SlideShare a Scribd company logo
Algorithmic Intelligence Lab
Algorithmic Intelligence Lab
Kimin Lee
Ph.D. student at KAIST
NAVER Tech Talk
Confident Deep Learning
Algorithmic Intelligence Lab
Outline
• Introduction
• Predictive uncertainty of deep neural networks
• Summary
• How to train confident neural networks
• Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution
Samples [Lee’ 18a]
• Applications
• Confident Multiple Choice Learning [Lee’ 17]
• Hierarchical novelty detection [Lee’ 18b]
• Conclusion
2
[Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I
n ICLR, 2018.
[Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017.
[Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
Algorithmic Intelligence Lab
• Supervised learning (e.g., regression and classification)
• Objective: finding an unknown target distribution, i.e., P(Y|X)
• Recent advances in deep learning have dramatically improved accuracy on
several supervised learning tasks
Introduction: Predictive uncertainty of deep neural networks (DNNs)
3
[Amodei’ 16] Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J.,
Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G. and
Chen, J. Deep speech 2: End-to-end speech recognition in english and
mandarin. In ICML, 2016.
[He’ 16] He, K., Zhang, X., Ren, S. and Sun, J. Deep residual learning for
image recognition. In CVPR, 2016.
[Hershey’ 17] Hershey, S., Chaudhuri, S., Ellis, D.P., Gemmeke, J.F., Jansen, A.,
Moore, R.C., Plakal, M., Platt, D., Saurous, R.A., Seybold, B. and Slaney, M.
CNN architectures for large-scale audio classification. In ICASSP, 2017.
[Girshick’ 15] Girshick, Ross. Fast r-cnn. In ICCV, pp. 1440–1448, 2015
Input space Output space
Objective detection [Girshick’ 15]
Speech recognition
[Amodei’ 16]
Image classification
[He’ 16]
Audio
recognition
[Hershey’ 17]
Algorithmic Intelligence Lab
• Uncertainty of predictive distribution is important in DNN’s applications
• What is predictive uncertainty?
• As a example, consider classification task
• It represents a confidence about prediction!
• For example, it can be measured as follows:
• Entropy of predictive distribution [Lakshminarayanan’ 17]
• Maximum value of predictive distribution [Hendrycks’ 17]
Introduction: Predictive uncertainty of deep neural networks (DNNs)
4
[Lakshminarayanan’ 17] Lakshminarayanan, B., Pritzel, A. and Blundell, C., Simple and scalable predictive uncertainty estimation using deep ensembles. In NIPS, 2017.
[Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017.
Persian
cat
tiger
cat
0.12
0.18
Persian
cat
dog
0.99
Algorithmic Intelligence Lab
• Predictive uncertainty is related to many machine learning problems:
• Predictive uncertainty is also indispensable when deploying DNNs in
real-world systems [Dario’ 16]
Introduction: Predictive uncertainty of deep neural networks (DNNs)
5
Autonomous drive Secure authentication system
[Dario’ 16] Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Mane ́. Concrete problems in ai safety. arXiv preprint arXiv:1606.06565, 2016.
[Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017.
[Guo’ 17] Guo, C., Pleiss, G., Sun, Y. and Weinberger, K.Q., 2017. On Calibration of Modern Neural Networks. In ICML 2017.
[Goodfellow’ 14] Goodfellow, I.J., Shlens, J. and Szegedy, C., 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572.
[Srivastava’ 14] Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R., Dropout: a simple way to prevent neural networks from overfitting. JMLR. 2014.
Novelty detection
[Hendrycks’ 17]
Adversarial detection
[Song’ 18]
Ensemble learning
[Lee’ 17]
Algorithmic Intelligence Lab
• However, DNNs do not capture their predictive uncertainty
• E.g., DNNs trained to classify MNIST images often produce high confident
probability 91% even for random noise [Henderycks’ 17]
• Challenge arises in improving the quality of the predictive uncertainty!
• Main topic of this presentation
• How to train confident neural networks?
• Training confidence-calibrated classifiers for detecting out-of-distribution
samples [Lee’ 18a]
• Applications
• Confident multiple choice learning [Lee’ 17]
• Hierarchical novelty detection [Lee’ 18b]
Introduction: Predictive uncertainty of deep neural networks (DNNs)
6
Unknown image Cat TrainDog
99%
[Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017.
[Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. In ICLR 2018.
[Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017.
[Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
Algorithmic Intelligence Lab
Outline
• Introduction
• Predictive uncertainty of deep neural networks
• Summary
• How to train confident neural networks
• Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution
Samples [Lee’ 18a]
• Applications
• Confident Multiple Choice Learning [Lee’ 17]
• Hierarchical novelty detection [Lee’ 18b]
• Conclusion
7
[Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I
n ICLR, 2018.
[Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017.
[Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
Algorithmic Intelligence Lab
• Related problem
• Detecting out-of-distribution [Hendrycks’ 17]
• Detect whether a test sample is from in-distribution (i.e., training distribution
by classifier) or out-of-distribution
• E.g., image classification
• Assume a classifier trains handwritten digits (denoted as in-distribution)
• Detecting out-of-distribution
• Performance of detector reflects confidence of predictive distribution!
How to Train Confident Neural Networks?
8
In-distribution Out-of-distribution
Predictive dist.
Data
[Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017.
[Guo’ 17] Guo, C., Pleiss, G., Sun, Y. and Weinberger, K.Q., 2017. On Calibration of Modern Neural Networks. In ICML 2017.
[Liang’ 17] Liang, S., Li, Y. and Srikant, R., 2017. Principled Detection of Out-of-Distribution Examples in Neural Networks. arXiv preprint arXiv:1706.02690.
Algorithmic Intelligence Lab
• Threshold-based Detector [Guo’ 17, Hendrycks’17, Liang’ 18]
• How to define the score?
• Baseline detector [Hendrycks’17]
• Confidence score = maximum value of predictive distribution
• Temperature scaling [Guo’ 17]
• Confidence score = maximum value of scaled predictive distribution
• Limitations
• Performance of prior works highly depends on how to train the classifiers
Related Work
9
[Input] [Classifier]
score
10
If score > 𝜖: In-distribution
Else: out-of-distribution
[Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017.
[Guo’ 17] Guo, C., Pleiss, G., Sun, Y. and Weinberger, K.Q., 2017. On Calibration of Modern Neural Networks. In ICML 2017.
[Liang’ 17] Liang, S., Li, Y. and Srikant, R., 2017. Principled Detection of Out-of-Distribution Examples in Neural Networks. In ICLR, 2018.
Output of neural networks
Algorithmic Intelligence Lab
• Main components of our contribution
• New loss
• Confident loss for confident classifier
• New generative adversarial network (GAN)
• GAN for generating out-of-distribution samples
• New training method
• Joint training of classifier and GAN
• Experimental results
• Our method drastically improves the detection performance
• VGGNet trained by our method improves TPR compared to the baseline:
• 14.0%39.1% and 46.3%  98.9% on CIFAR-10 and SVHN, respectively
• Providing visual understandings on the proposed method
Our Contributions
10
Algorithmic Intelligence Lab
• Confident loss
• Minimize the KL divergence on data from out-of-distribution
• Interpretation
• Assigning higher maximum prediction values to in-distribution samples than o
ut-of-distribution ones
Contribution 1: Confident Loss
11
Data from in-dist Data from out-of-dist
Data distribution Uniform distribution
“Zero confidence”
Algorithmic Intelligence Lab
• Confident loss
• Minimize the KL divergence on data from out-of-distribution
• Interpretation
• Assigning higher maximum prediction values to in-distribution samples than o
ut-of-distribution ones
• Effects of confidence loss
• Fraction of the maximum prediction value from simple CNNs (2 Conv + 3 FC)
• KL divergence term is optimized using CIFAR-10 training data
Contribution 1: Confident Loss
12
Data from in-dist Data from out-of-dist
Algorithmic Intelligence Lab
• Main issues of confidence loss
• How to optimize the KL divergence loss?
• The number of out-of-distribution samples might be almost infinite to cover
the entire space
• Our intuition
• Samples close to in-distribution could be more effective in improving the
detection performance
Contribution 2. GAN for Generating Out-of-Distribution Samples
13
Algorithmic Intelligence Lab
• New GAN objective
• Term (a) forces the generator to generate low-density samples
• (approximately) minimizing the log negative likelihood of in-distribution
• Term (b) corresponds to the original GAN loss
• Generating out-of-distribution samples close to in-distribution
• Experimental results on toy example and MNIST
Contribution 2. GAN for Generating Out-of-Distribution Samples
14
Algorithmic Intelligence Lab
• We suggest training the proposed GAN using a confident classifier
• Converse is also possible
• We propose a joint confidence loss
• Classifier’s confidence loss: (c) + (d)
• GAN loss: (d) + (e)
• Alternating algorithm for optimizing the joint confidence loss
Contribution 3. Joint Confidence Loss
15
Step 2. update classifier
Classifier
GAN
Step 1. update GAN
Classifier
GAN
Algorithmic Intelligence Lab
• TP = true positive
• FN = false negative
• TN = true negative
• FP = false positive
• FPR at 95% TPR
• FPR = FP/(FP + TN), TPR = TP/(TP + FN)
• AUROC (Area Under the Receiver Operating Characteristic curve)
• ROC curve = relationship between TPR and FPR
• Detection Error
• Minimum misclassification probability over all thresholds
• AUPR (Area under the Precision-Recall curve)
• PR curve = relationship between precision=TP/(TP+FP) and recall=TP/(TP+FN)
Experimental Results - Metric
16
Algorithmic Intelligence Lab
• Measure the detection performance of threshold-based detectors
• Confidence loss with some explicit out-of-distribution dataset
• Classifier trained by our method drastically improves the detection
performance across all out-of-distributions
Experimental Results
17
Realistic images such as TinyImageNet (aqua line) and
LSUN(green line) are more useful than synthetic datasets
(orange line) for improving the detection perfor-mance
Algorithmic Intelligence Lab
• Joint confidence loss
• Confidence loss with the original GAN (orange bar) is often useful for
improving the detection performance
• Joint confidence loss (bluebar) still outperforms all baseline it in all cases
Experimental Results
18
Algorithmic Intelligence Lab
• Interpretability of trained classifier
• Classifier trained by cross entropy loss shows sharp gradient maps for both
samples from in- and out-of-distributions
• Classifiers trained by the confidence losses do only on samples from in-
distribution.
Experimental Results
19
Algorithmic Intelligence Lab
Outline
• Introduction
• Predictive uncertainty of deep neural networks
• Summary
• How to train confident neural networks
• Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution
Samples [Lee’ 18a]
• Applications
• Confident Multiple Choice Learning [Lee’ 17]
• Hierarchical novelty detection [Lee’ 18b]
• Conclusion
20
[Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I
n ICLR, 2018.
[Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017.
[Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
Algorithmic Intelligence Lab
• Ensemble learning
• Train multiple models to try and solve the same problem
• Combine the outputs of them to obtain the final decision
• Bagging [Breiman’ 96], boosting [Freund’ 99] and mixture of experts
[Jacobs’ 91]
Application: Ensemble Learning using Deep Neural Networks
21
Final decision
Majority
voting
Test data
[Freund’ 99] Freund, Yoav, Schapire, Robert, and Abe, N. A short introduction to boosting. Journal-Japanese Society For Arti- ficial Intelligence, 14(771-780):1612, 1999.
[Breiman’ 96] Breiman, Leo. Bagging predictors. Machine learning, 24 (2):123–140, 1996.
[Jacobs’ 91] Jacobs, Robert A, Jordan, Michael I, Nowlan, Steven J, and Hinton, Geoffrey E. Adaptive mixtures of local experts. Neural computation, 1991.
Algorithmic Intelligence Lab
• Independent Ensemble (IE) [Ciregan’ 12]
• Independently train each model with random initialization
• IE generally improves the performance by reducing the variance
• Multiple choice learning (MCL) [Guzman’ 12]
• Making each model specialized for certain subset of data
• MCL can produce diverse solutions
• Image classification on CIFAR-10 using 5 CNNs
Ensemble Methods for Deep Neural Networks
22
Algorithmic Intelligence Lab
• Multiple choice learning (MCL) [Guzman’ 12]
• Making each model specialized for certain subset of data
• Overconfidence issues of MCL
Ensemble Methods for Deep Neural Networks
23
Cat
Cat
Model 1 (specialized in “Cat” image)
Model 2 (specialized in “Dog” image)Dog
Dog
Algorithmic Intelligence Lab
• Multiple choice learning (MCL) [Guzman’ 12]
• Making each model specialized for certain subset of data
• Overconfidence issues of MCL
Ensemble Methods for Deep Neural Networks
24
Cat
Cat
Model 1 (specialized in “Cat” image)
Model 2 (specialized in “Dog” image)Dog
Dog
Cat Overconfident
1%
99%
97%
3%
Algorithmic Intelligence Lab
• Multiple choice learning (MCL) [Guzman’ 12]
• Making each model specialized for certain subset of data
• Overconfidence issues of MCL
Ensemble Methods for Deep Neural Networks
25
Cat
Cat
Model 1 (specialized in “Cat” image)
Model 2 (specialized in “Dog” image)Dog
Dog
Cat
1%
99%
97%
3%
DogCat
49% 51%
Averaged probability
Average
Voting
Algorithmic Intelligence Lab
• Making the specialized models with confident predictions
• Main components of our contributions
• Experiments on CIFAR-10 using 5 CNNs (2 Conv + 2 FC)
Confident Multiple Choice Learning (CMCL)
26
New loss: confident oracle loss
New architecture: feature sharing
New training method: random labeling
Algorithmic Intelligence Lab
• Confident oracle loss
• Generating confident predictions by minimizing the KL divergence
Confident Oracle Loss
27
Algorithmic Intelligence Lab
• Confident oracle loss
• Generating confident predictions by minimizing the KL divergence
Confident Oracle Loss
28
Model 1 Model 2 Model 3
Data distribution
Algorithmic Intelligence Lab
• Confident oracle loss
• Generating confident predictions by minimizing the KL divergence
Confident Oracle Loss
29
Model 1 Model 2 Model 3
Data distribution Uniform distribution
Algorithmic Intelligence Lab
• Classification test set error rates on CIFAR-10 and SVHN
• Top-1 error
• Select the class from averaged probability
• Oracle error
• Measuring whether none of the members predict the correct class
• We use both feature sharing and random labeling for all experiments
Experimental Results: Image Classification
30
• 32 × 32 RGB
• 10 classes
• 50,000 training set
• 10,000 test set
• 32 × 32 RGB
• 10 classes
• 73,257 training set
• 26,032 test set
CIFAR-10 [Krizhevsky’ 09] SVHN [Netzer’ 11]
Algorithmic Intelligence Lab
• Ensemble of small-scale CNNs (2 Conv + 2 FC)
Experimental Results: Image Classification
31
K=1 K=2
Model 1
Model 2
Model 3
Model 1
Model 2
Model 3
“Picking K specialized models”
Algorithmic Intelligence Lab
• Ensemble of small-scale CNNs (2 Conv + 2 FC)
• Ensemble of 5 large-scale CNNs
Experimental Results: Image Classification
32
Algorithmic Intelligence Lab
• iCoseg dataset
Experimental Results: Image Segmentation
33
Fully convolutional neural networks
(FCNs) [Long’ 15]
Pixel-level classification
problem with 2 classes
1(foreground) and 0 (background)
[Long’ 15] Long, J., Shelhamer, E. and Darrell, T. Fully convolutional networks for semantic segmentation. In CVPR, 2015.
Algorithmic Intelligence Lab
• Prediction results of segmentation for few sample images
• MCL and CMCL generate high-quality predictions
• CMCL only outperforms IE in terms of the top-1 error
Experimental Results: Image Segmentation
34
- 6.77%
relative
reduction
Algorithmic Intelligence Lab
Outline
• Introduction
• Predictive uncertainty of deep neural networks
• Summary
• How to train confident neural networks
• Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution
Samples [Lee’ 18a]
• Applications
• Confident Multiple Choice Learning [Lee’ 17]
• Hierarchical novelty detection [Lee’ 18b]
• Conclusion
35
[Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I
n ICLR, 2018.
[Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017.
[Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
Algorithmic Intelligence Lab
• Objective
• 1. Find the closest known (super-)category in taxonomy
• 2. Find fine-grained classification for novel categories (i.e., out-of-
distribution samples)
Hierarchical Novelty Detection
36
Figure 1. An illustration of our hierarchical novelty detection task
Algorithmic Intelligence Lab
• Top-down method (TD)
• p(child) = ∑super p(child | super) p(super)
• Objective
• Inference
• Definition of confidence:
Two Main Approaches
37
Novel class
Algorithmic Intelligence Lab
• ImageNet dataset
• 22K classes
• Taxonomy
• 396 super classes of 1K known
leaf classes
• Rest of 21K classes can be used
as novel class
• Example
Experimental Results on ImageNet Dataset
38
[Deng’ 12] J. Deng, J. Krause, A. C. Berg, and L. Fei-Fei. Hedging your bets: Optimizing accuracy-specificity trade offs in large scale visual recognition. In
CVPR , pages 3450–3457. IEEE, 2012.
• Hierarchical novelty detection
performance
• Baseline: DARTS [Deng’ 12]
• One can note that our methods
have higher novel class
accuracy than DARTS to have a
same known class accuracy in
most regions
Algorithmic Intelligence Lab
• We propose a new method for training confident deep neural networks
• It produce the uniform distribution when the input is not from target
distribution
• We show that it can be applied to many machine learning problems:
• Detecting out-of-distribution problem
• Ensemble learning using deep neural networks
• Hierarchical novelty detection
• We believe that our new approach brings a refreshing angle for
developing confident deep networks in many related applications:
• Network calibration
• Adversarial example detection
• Bayesian probabilistic models
• Semi-supervised learning
Conclusion
39

More Related Content

What's hot

Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...
tomoaki0705
 
Wasserstein GAN
Wasserstein GANWasserstein GAN
Wasserstein GAN
Bar Vinograd
 
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
Takayoshi Yamashita
 
東京都市大学 データ解析入門 3 行列分解 2
東京都市大学 データ解析入門 3 行列分解 2東京都市大学 データ解析入門 3 行列分解 2
東京都市大学 データ解析入門 3 行列分解 2
hirokazutanaka
 
Humpback whale identification challenge反省会
Humpback whale identification challenge反省会Humpback whale identification challenge反省会
Humpback whale identification challenge反省会
Yusuke Uchida
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
Deep Learning JP
 
トピックモデルの評価指標 Perplexity とは何なのか?
トピックモデルの評価指標 Perplexity とは何なのか?トピックモデルの評価指標 Perplexity とは何なのか?
トピックモデルの評価指標 Perplexity とは何なのか?
hoxo_m
 
【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...
【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...
【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...
Deep Learning JP
 
Merülés táblázat használata
Merülés táblázat használataMerülés táblázat használata
Merülés táblázat használata
Andrea Kiss
 
R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)
R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)
R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)
Koichi Hamada
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
Deep Learning JP
 
動画像理解のための深層学習アプローチ Deep learning approaches to video understanding
動画像理解のための深層学習アプローチ Deep learning approaches to video understanding動画像理解のための深層学習アプローチ Deep learning approaches to video understanding
動画像理解のための深層学習アプローチ Deep learning approaches to video understanding
Toru Tamaki
 
[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning
[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning
[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning
Deep Learning JP
 
SSII2020 [O3-01] Extreme 3D センシング
SSII2020 [O3-01]  Extreme 3D センシングSSII2020 [O3-01]  Extreme 3D センシング
SSII2020 [O3-01] Extreme 3D センシング
SSII
 
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
Bang Xiang Yong
 
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII
 
Semi supervised, weakly-supervised, unsupervised, and active learning
Semi supervised, weakly-supervised, unsupervised, and active learningSemi supervised, weakly-supervised, unsupervised, and active learning
Semi supervised, weakly-supervised, unsupervised, and active learning
Yusuke Uchida
 
MLIP - Chapter 5 - Detection, Segmentation, Captioning
MLIP - Chapter 5 - Detection, Segmentation, CaptioningMLIP - Chapter 5 - Detection, Segmentation, Captioning
MLIP - Chapter 5 - Detection, Segmentation, Captioning
Charles Deledalle
 
[DL輪読会]Vector-based navigation using grid-like representations in artificial ...
[DL輪読会]Vector-based navigation using grid-like representations in artificial ...[DL輪読会]Vector-based navigation using grid-like representations in artificial ...
[DL輪読会]Vector-based navigation using grid-like representations in artificial ...
Deep Learning JP
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
Deep Learning JP
 

What's hot (20)

Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera w...
 
Wasserstein GAN
Wasserstein GANWasserstein GAN
Wasserstein GAN
 
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
 
東京都市大学 データ解析入門 3 行列分解 2
東京都市大学 データ解析入門 3 行列分解 2東京都市大学 データ解析入門 3 行列分解 2
東京都市大学 データ解析入門 3 行列分解 2
 
Humpback whale identification challenge反省会
Humpback whale identification challenge反省会Humpback whale identification challenge反省会
Humpback whale identification challenge反省会
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
 
トピックモデルの評価指標 Perplexity とは何なのか?
トピックモデルの評価指標 Perplexity とは何なのか?トピックモデルの評価指標 Perplexity とは何なのか?
トピックモデルの評価指標 Perplexity とは何なのか?
 
【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...
【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...
【DL輪読会】Representational Continuity for Unsupervised Continual Learning ( ICLR...
 
Merülés táblázat használata
Merülés táblázat használataMerülés táblázat használata
Merülés táblázat használata
 
R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)
R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)
R言語による アソシエーション分析-組合せ・事象の規則を解明する-(第5回R勉強会@東京)
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
 
動画像理解のための深層学習アプローチ Deep learning approaches to video understanding
動画像理解のための深層学習アプローチ Deep learning approaches to video understanding動画像理解のための深層学習アプローチ Deep learning approaches to video understanding
動画像理解のための深層学習アプローチ Deep learning approaches to video understanding
 
[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning
[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning
[DL輪読会]Randomized Prior Functions for Deep Reinforcement Learning
 
SSII2020 [O3-01] Extreme 3D センシング
SSII2020 [O3-01]  Extreme 3D センシングSSII2020 [O3-01]  Extreme 3D センシング
SSII2020 [O3-01] Extreme 3D センシング
 
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
 
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
 
Semi supervised, weakly-supervised, unsupervised, and active learning
Semi supervised, weakly-supervised, unsupervised, and active learningSemi supervised, weakly-supervised, unsupervised, and active learning
Semi supervised, weakly-supervised, unsupervised, and active learning
 
MLIP - Chapter 5 - Detection, Segmentation, Captioning
MLIP - Chapter 5 - Detection, Segmentation, CaptioningMLIP - Chapter 5 - Detection, Segmentation, Captioning
MLIP - Chapter 5 - Detection, Segmentation, Captioning
 
[DL輪読会]Vector-based navigation using grid-like representations in artificial ...
[DL輪読会]Vector-based navigation using grid-like representations in artificial ...[DL輪読会]Vector-based navigation using grid-like representations in artificial ...
[DL輪読会]Vector-based navigation using grid-like representations in artificial ...
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
 

Similar to Predictive uncertainty of deep models and its applications

Robust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labelsRobust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labels
Kimin Lee
 
Introduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging ApplicationsIntroduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging Applications
Walter Hugo Lopez Pinaya
 
OOD_PPT.pptx
OOD_PPT.pptxOOD_PPT.pptx
OOD_PPT.pptx
YashBhatnagar30
 
Zero shot-learning: paper presentation
Zero shot-learning: paper presentationZero shot-learning: paper presentation
Zero shot-learning: paper presentation
Jérémie Kalfon
 
Crowdsourced Object Segmentation with a Game
Crowdsourced Object Segmentation with a GameCrowdsourced Object Segmentation with a Game
Crowdsourced Object Segmentation with a Game
Universitat Politècnica de Catalunya
 
final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...
final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...
final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...
SharaneshUpase1
 
CS194Lec0hbh6EDA.pptx
CS194Lec0hbh6EDA.pptxCS194Lec0hbh6EDA.pptx
CS194Lec0hbh6EDA.pptx
PrudhvirajEluri1
 
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
ALINLAB
 
A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...
A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...
A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...
Data Con LA
 
Introduction to Interpretable Machine Learning
Introduction to Interpretable Machine LearningIntroduction to Interpretable Machine Learning
Introduction to Interpretable Machine Learning
Nguyen Giang
 
Talk@rmit 09112017
Talk@rmit 09112017Talk@rmit 09112017
Talk@rmit 09112017
Shuai Zhang
 
Throttling Malware Families in 2D
Throttling Malware Families in 2DThrottling Malware Families in 2D
Throttling Malware Families in 2D
Mohamed Nassar
 
Sybrandt Thesis Proposal Presentation
Sybrandt Thesis Proposal PresentationSybrandt Thesis Proposal Presentation
Sybrandt Thesis Proposal Presentation
Justin Sybrandt, Ph.D.
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Seonho Park
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANs
Parham Zilouchian
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
Yogendra Tamang
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
Egyptian Engineers Association
 
PPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at UberPPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at Uber
Jisang Yoon
 
imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdf
KammetaJoshna
 

Similar to Predictive uncertainty of deep models and its applications (20)

Robust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labelsRobust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labels
 
Introduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging ApplicationsIntroduction to Deep Learning and some Neuroimaging Applications
Introduction to Deep Learning and some Neuroimaging Applications
 
OOD_PPT.pptx
OOD_PPT.pptxOOD_PPT.pptx
OOD_PPT.pptx
 
Zero shot-learning: paper presentation
Zero shot-learning: paper presentationZero shot-learning: paper presentation
Zero shot-learning: paper presentation
 
Crowdsourced Object Segmentation with a Game
Crowdsourced Object Segmentation with a GameCrowdsourced Object Segmentation with a Game
Crowdsourced Object Segmentation with a Game
 
final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...
final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...
final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) ...
 
CS194Lec0hbh6EDA.pptx
CS194Lec0hbh6EDA.pptxCS194Lec0hbh6EDA.pptx
CS194Lec0hbh6EDA.pptx
 
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
 
A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...
A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...
A Practical Use of Artificial Intelligence in the Fight Against Cancer by Bri...
 
CSU_comp
CSU_compCSU_comp
CSU_comp
 
Introduction to Interpretable Machine Learning
Introduction to Interpretable Machine LearningIntroduction to Interpretable Machine Learning
Introduction to Interpretable Machine Learning
 
Talk@rmit 09112017
Talk@rmit 09112017Talk@rmit 09112017
Talk@rmit 09112017
 
Throttling Malware Families in 2D
Throttling Malware Families in 2DThrottling Malware Families in 2D
Throttling Malware Families in 2D
 
Sybrandt Thesis Proposal Presentation
Sybrandt Thesis Proposal PresentationSybrandt Thesis Proposal Presentation
Sybrandt Thesis Proposal Presentation
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANs
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
 
PPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at UberPPT - Deep and Confident Prediction For Time Series at Uber
PPT - Deep and Confident Prediction For Time Series at Uber
 
imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdf
 

More from NAVER Engineering

React vac pattern
React vac patternReact vac pattern
React vac pattern
NAVER Engineering
 
디자인 시스템에 직방 ZUIX
디자인 시스템에 직방 ZUIX디자인 시스템에 직방 ZUIX
디자인 시스템에 직방 ZUIX
NAVER Engineering
 
진화하는 디자인 시스템(걸음마 편)
진화하는 디자인 시스템(걸음마 편)진화하는 디자인 시스템(걸음마 편)
진화하는 디자인 시스템(걸음마 편)
NAVER Engineering
 
서비스 운영을 위한 디자인시스템 프로젝트
서비스 운영을 위한 디자인시스템 프로젝트서비스 운영을 위한 디자인시스템 프로젝트
서비스 운영을 위한 디자인시스템 프로젝트
NAVER Engineering
 
BPL(Banksalad Product Language) 무야호
BPL(Banksalad Product Language) 무야호BPL(Banksalad Product Language) 무야호
BPL(Banksalad Product Language) 무야호
NAVER Engineering
 
이번 생에 디자인 시스템은 처음이라
이번 생에 디자인 시스템은 처음이라이번 생에 디자인 시스템은 처음이라
이번 생에 디자인 시스템은 처음이라
NAVER Engineering
 
날고 있는 여러 비행기 넘나 들며 정비하기
날고 있는 여러 비행기 넘나 들며 정비하기날고 있는 여러 비행기 넘나 들며 정비하기
날고 있는 여러 비행기 넘나 들며 정비하기
NAVER Engineering
 
쏘카프레임 구축 배경과 과정
 쏘카프레임 구축 배경과 과정 쏘카프레임 구축 배경과 과정
쏘카프레임 구축 배경과 과정
NAVER Engineering
 
플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기
플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기
플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기
NAVER Engineering
 
200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)
200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)
200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)
NAVER Engineering
 
200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드
200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드
200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드
NAVER Engineering
 
200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기
200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기
200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기
NAVER Engineering
 
200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활
200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활
200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활
NAVER Engineering
 
200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출
200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출
200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출
NAVER Engineering
 
200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우
200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우
200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우
NAVER Engineering
 
200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...
200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...
200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...
NAVER Engineering
 
200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법
200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법
200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법
NAVER Engineering
 
200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며
200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며
200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며
NAVER Engineering
 
200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기
200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기
200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기
NAVER Engineering
 
200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기
200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기
200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기
NAVER Engineering
 

More from NAVER Engineering (20)

React vac pattern
React vac patternReact vac pattern
React vac pattern
 
디자인 시스템에 직방 ZUIX
디자인 시스템에 직방 ZUIX디자인 시스템에 직방 ZUIX
디자인 시스템에 직방 ZUIX
 
진화하는 디자인 시스템(걸음마 편)
진화하는 디자인 시스템(걸음마 편)진화하는 디자인 시스템(걸음마 편)
진화하는 디자인 시스템(걸음마 편)
 
서비스 운영을 위한 디자인시스템 프로젝트
서비스 운영을 위한 디자인시스템 프로젝트서비스 운영을 위한 디자인시스템 프로젝트
서비스 운영을 위한 디자인시스템 프로젝트
 
BPL(Banksalad Product Language) 무야호
BPL(Banksalad Product Language) 무야호BPL(Banksalad Product Language) 무야호
BPL(Banksalad Product Language) 무야호
 
이번 생에 디자인 시스템은 처음이라
이번 생에 디자인 시스템은 처음이라이번 생에 디자인 시스템은 처음이라
이번 생에 디자인 시스템은 처음이라
 
날고 있는 여러 비행기 넘나 들며 정비하기
날고 있는 여러 비행기 넘나 들며 정비하기날고 있는 여러 비행기 넘나 들며 정비하기
날고 있는 여러 비행기 넘나 들며 정비하기
 
쏘카프레임 구축 배경과 과정
 쏘카프레임 구축 배경과 과정 쏘카프레임 구축 배경과 과정
쏘카프레임 구축 배경과 과정
 
플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기
플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기
플랫폼 디자이너 없이 디자인 시스템을 구축하는 프로덕트 디자이너의 우당탕탕 고통 연대기
 
200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)
200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)
200820 NAVER TECH CONCERT 15_Code Review is Horse(코드리뷰는 말이야)(feat.Latte)
 
200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드
200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드
200819 NAVER TECH CONCERT 03_화려한 코루틴이 내 앱을 감싸네! 코루틴으로 작성해보는 깔끔한 비동기 코드
 
200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기
200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기
200819 NAVER TECH CONCERT 10_맥북에서도 아이맥프로에서 빌드하는 것처럼 빌드 속도 빠르게 하기
 
200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활
200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활
200819 NAVER TECH CONCERT 08_성능을 고민하는 슬기로운 개발자 생활
 
200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출
200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출
200819 NAVER TECH CONCERT 05_모르면 손해보는 Android 디버깅/분석 꿀팁 대방출
 
200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우
200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우
200819 NAVER TECH CONCERT 09_Case.xcodeproj - 좋은 동료로 거듭나기 위한 노하우
 
200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...
200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...
200820 NAVER TECH CONCERT 14_야 너두 할 수 있어. 비전공자, COBOL 개발자를 거쳐 네이버에서 FE 개발하게 된...
 
200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법
200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법
200820 NAVER TECH CONCERT 13_네이버에서 오픈 소스 개발을 통해 성장하는 방법
 
200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며
200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며
200820 NAVER TECH CONCERT 12_상반기 네이버 인턴을 돌아보며
 
200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기
200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기
200820 NAVER TECH CONCERT 11_빠르게 성장하는 슈퍼루키로 거듭나기
 
200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기
200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기
200819 NAVER TECH CONCERT 07_신입 iOS 개발자 개발업무 적응기
 

Recently uploaded

FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Product School
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Product School
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
Alison B. Lowndes
 

Recently uploaded (20)

FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 

Predictive uncertainty of deep models and its applications

  • 1. Algorithmic Intelligence Lab Algorithmic Intelligence Lab Kimin Lee Ph.D. student at KAIST NAVER Tech Talk Confident Deep Learning
  • 2. Algorithmic Intelligence Lab Outline • Introduction • Predictive uncertainty of deep neural networks • Summary • How to train confident neural networks • Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution Samples [Lee’ 18a] • Applications • Confident Multiple Choice Learning [Lee’ 17] • Hierarchical novelty detection [Lee’ 18b] • Conclusion 2 [Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I n ICLR, 2018. [Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017. [Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
  • 3. Algorithmic Intelligence Lab • Supervised learning (e.g., regression and classification) • Objective: finding an unknown target distribution, i.e., P(Y|X) • Recent advances in deep learning have dramatically improved accuracy on several supervised learning tasks Introduction: Predictive uncertainty of deep neural networks (DNNs) 3 [Amodei’ 16] Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G. and Chen, J. Deep speech 2: End-to-end speech recognition in english and mandarin. In ICML, 2016. [He’ 16] He, K., Zhang, X., Ren, S. and Sun, J. Deep residual learning for image recognition. In CVPR, 2016. [Hershey’ 17] Hershey, S., Chaudhuri, S., Ellis, D.P., Gemmeke, J.F., Jansen, A., Moore, R.C., Plakal, M., Platt, D., Saurous, R.A., Seybold, B. and Slaney, M. CNN architectures for large-scale audio classification. In ICASSP, 2017. [Girshick’ 15] Girshick, Ross. Fast r-cnn. In ICCV, pp. 1440–1448, 2015 Input space Output space Objective detection [Girshick’ 15] Speech recognition [Amodei’ 16] Image classification [He’ 16] Audio recognition [Hershey’ 17]
  • 4. Algorithmic Intelligence Lab • Uncertainty of predictive distribution is important in DNN’s applications • What is predictive uncertainty? • As a example, consider classification task • It represents a confidence about prediction! • For example, it can be measured as follows: • Entropy of predictive distribution [Lakshminarayanan’ 17] • Maximum value of predictive distribution [Hendrycks’ 17] Introduction: Predictive uncertainty of deep neural networks (DNNs) 4 [Lakshminarayanan’ 17] Lakshminarayanan, B., Pritzel, A. and Blundell, C., Simple and scalable predictive uncertainty estimation using deep ensembles. In NIPS, 2017. [Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017. Persian cat tiger cat 0.12 0.18 Persian cat dog 0.99
  • 5. Algorithmic Intelligence Lab • Predictive uncertainty is related to many machine learning problems: • Predictive uncertainty is also indispensable when deploying DNNs in real-world systems [Dario’ 16] Introduction: Predictive uncertainty of deep neural networks (DNNs) 5 Autonomous drive Secure authentication system [Dario’ 16] Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Mane ́. Concrete problems in ai safety. arXiv preprint arXiv:1606.06565, 2016. [Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017. [Guo’ 17] Guo, C., Pleiss, G., Sun, Y. and Weinberger, K.Q., 2017. On Calibration of Modern Neural Networks. In ICML 2017. [Goodfellow’ 14] Goodfellow, I.J., Shlens, J. and Szegedy, C., 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572. [Srivastava’ 14] Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R., Dropout: a simple way to prevent neural networks from overfitting. JMLR. 2014. Novelty detection [Hendrycks’ 17] Adversarial detection [Song’ 18] Ensemble learning [Lee’ 17]
  • 6. Algorithmic Intelligence Lab • However, DNNs do not capture their predictive uncertainty • E.g., DNNs trained to classify MNIST images often produce high confident probability 91% even for random noise [Henderycks’ 17] • Challenge arises in improving the quality of the predictive uncertainty! • Main topic of this presentation • How to train confident neural networks? • Training confidence-calibrated classifiers for detecting out-of-distribution samples [Lee’ 18a] • Applications • Confident multiple choice learning [Lee’ 17] • Hierarchical novelty detection [Lee’ 18b] Introduction: Predictive uncertainty of deep neural networks (DNNs) 6 Unknown image Cat TrainDog 99% [Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017. [Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. In ICLR 2018. [Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017. [Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
  • 7. Algorithmic Intelligence Lab Outline • Introduction • Predictive uncertainty of deep neural networks • Summary • How to train confident neural networks • Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution Samples [Lee’ 18a] • Applications • Confident Multiple Choice Learning [Lee’ 17] • Hierarchical novelty detection [Lee’ 18b] • Conclusion 7 [Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I n ICLR, 2018. [Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017. [Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
  • 8. Algorithmic Intelligence Lab • Related problem • Detecting out-of-distribution [Hendrycks’ 17] • Detect whether a test sample is from in-distribution (i.e., training distribution by classifier) or out-of-distribution • E.g., image classification • Assume a classifier trains handwritten digits (denoted as in-distribution) • Detecting out-of-distribution • Performance of detector reflects confidence of predictive distribution! How to Train Confident Neural Networks? 8 In-distribution Out-of-distribution Predictive dist. Data [Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017. [Guo’ 17] Guo, C., Pleiss, G., Sun, Y. and Weinberger, K.Q., 2017. On Calibration of Modern Neural Networks. In ICML 2017. [Liang’ 17] Liang, S., Li, Y. and Srikant, R., 2017. Principled Detection of Out-of-Distribution Examples in Neural Networks. arXiv preprint arXiv:1706.02690.
  • 9. Algorithmic Intelligence Lab • Threshold-based Detector [Guo’ 17, Hendrycks’17, Liang’ 18] • How to define the score? • Baseline detector [Hendrycks’17] • Confidence score = maximum value of predictive distribution • Temperature scaling [Guo’ 17] • Confidence score = maximum value of scaled predictive distribution • Limitations • Performance of prior works highly depends on how to train the classifiers Related Work 9 [Input] [Classifier] score 10 If score > 𝜖: In-distribution Else: out-of-distribution [Henderycks’ 17] Hendrycks, D. and Gimpel, K., A baseline for detecting misclassified and out-of-distribution examples in neural networks. In ICLR 2017. [Guo’ 17] Guo, C., Pleiss, G., Sun, Y. and Weinberger, K.Q., 2017. On Calibration of Modern Neural Networks. In ICML 2017. [Liang’ 17] Liang, S., Li, Y. and Srikant, R., 2017. Principled Detection of Out-of-Distribution Examples in Neural Networks. In ICLR, 2018. Output of neural networks
  • 10. Algorithmic Intelligence Lab • Main components of our contribution • New loss • Confident loss for confident classifier • New generative adversarial network (GAN) • GAN for generating out-of-distribution samples • New training method • Joint training of classifier and GAN • Experimental results • Our method drastically improves the detection performance • VGGNet trained by our method improves TPR compared to the baseline: • 14.0%39.1% and 46.3%  98.9% on CIFAR-10 and SVHN, respectively • Providing visual understandings on the proposed method Our Contributions 10
  • 11. Algorithmic Intelligence Lab • Confident loss • Minimize the KL divergence on data from out-of-distribution • Interpretation • Assigning higher maximum prediction values to in-distribution samples than o ut-of-distribution ones Contribution 1: Confident Loss 11 Data from in-dist Data from out-of-dist Data distribution Uniform distribution “Zero confidence”
  • 12. Algorithmic Intelligence Lab • Confident loss • Minimize the KL divergence on data from out-of-distribution • Interpretation • Assigning higher maximum prediction values to in-distribution samples than o ut-of-distribution ones • Effects of confidence loss • Fraction of the maximum prediction value from simple CNNs (2 Conv + 3 FC) • KL divergence term is optimized using CIFAR-10 training data Contribution 1: Confident Loss 12 Data from in-dist Data from out-of-dist
  • 13. Algorithmic Intelligence Lab • Main issues of confidence loss • How to optimize the KL divergence loss? • The number of out-of-distribution samples might be almost infinite to cover the entire space • Our intuition • Samples close to in-distribution could be more effective in improving the detection performance Contribution 2. GAN for Generating Out-of-Distribution Samples 13
  • 14. Algorithmic Intelligence Lab • New GAN objective • Term (a) forces the generator to generate low-density samples • (approximately) minimizing the log negative likelihood of in-distribution • Term (b) corresponds to the original GAN loss • Generating out-of-distribution samples close to in-distribution • Experimental results on toy example and MNIST Contribution 2. GAN for Generating Out-of-Distribution Samples 14
  • 15. Algorithmic Intelligence Lab • We suggest training the proposed GAN using a confident classifier • Converse is also possible • We propose a joint confidence loss • Classifier’s confidence loss: (c) + (d) • GAN loss: (d) + (e) • Alternating algorithm for optimizing the joint confidence loss Contribution 3. Joint Confidence Loss 15 Step 2. update classifier Classifier GAN Step 1. update GAN Classifier GAN
  • 16. Algorithmic Intelligence Lab • TP = true positive • FN = false negative • TN = true negative • FP = false positive • FPR at 95% TPR • FPR = FP/(FP + TN), TPR = TP/(TP + FN) • AUROC (Area Under the Receiver Operating Characteristic curve) • ROC curve = relationship between TPR and FPR • Detection Error • Minimum misclassification probability over all thresholds • AUPR (Area under the Precision-Recall curve) • PR curve = relationship between precision=TP/(TP+FP) and recall=TP/(TP+FN) Experimental Results - Metric 16
  • 17. Algorithmic Intelligence Lab • Measure the detection performance of threshold-based detectors • Confidence loss with some explicit out-of-distribution dataset • Classifier trained by our method drastically improves the detection performance across all out-of-distributions Experimental Results 17 Realistic images such as TinyImageNet (aqua line) and LSUN(green line) are more useful than synthetic datasets (orange line) for improving the detection perfor-mance
  • 18. Algorithmic Intelligence Lab • Joint confidence loss • Confidence loss with the original GAN (orange bar) is often useful for improving the detection performance • Joint confidence loss (bluebar) still outperforms all baseline it in all cases Experimental Results 18
  • 19. Algorithmic Intelligence Lab • Interpretability of trained classifier • Classifier trained by cross entropy loss shows sharp gradient maps for both samples from in- and out-of-distributions • Classifiers trained by the confidence losses do only on samples from in- distribution. Experimental Results 19
  • 20. Algorithmic Intelligence Lab Outline • Introduction • Predictive uncertainty of deep neural networks • Summary • How to train confident neural networks • Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution Samples [Lee’ 18a] • Applications • Confident Multiple Choice Learning [Lee’ 17] • Hierarchical novelty detection [Lee’ 18b] • Conclusion 20 [Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I n ICLR, 2018. [Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017. [Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
  • 21. Algorithmic Intelligence Lab • Ensemble learning • Train multiple models to try and solve the same problem • Combine the outputs of them to obtain the final decision • Bagging [Breiman’ 96], boosting [Freund’ 99] and mixture of experts [Jacobs’ 91] Application: Ensemble Learning using Deep Neural Networks 21 Final decision Majority voting Test data [Freund’ 99] Freund, Yoav, Schapire, Robert, and Abe, N. A short introduction to boosting. Journal-Japanese Society For Arti- ficial Intelligence, 14(771-780):1612, 1999. [Breiman’ 96] Breiman, Leo. Bagging predictors. Machine learning, 24 (2):123–140, 1996. [Jacobs’ 91] Jacobs, Robert A, Jordan, Michael I, Nowlan, Steven J, and Hinton, Geoffrey E. Adaptive mixtures of local experts. Neural computation, 1991.
  • 22. Algorithmic Intelligence Lab • Independent Ensemble (IE) [Ciregan’ 12] • Independently train each model with random initialization • IE generally improves the performance by reducing the variance • Multiple choice learning (MCL) [Guzman’ 12] • Making each model specialized for certain subset of data • MCL can produce diverse solutions • Image classification on CIFAR-10 using 5 CNNs Ensemble Methods for Deep Neural Networks 22
  • 23. Algorithmic Intelligence Lab • Multiple choice learning (MCL) [Guzman’ 12] • Making each model specialized for certain subset of data • Overconfidence issues of MCL Ensemble Methods for Deep Neural Networks 23 Cat Cat Model 1 (specialized in “Cat” image) Model 2 (specialized in “Dog” image)Dog Dog
  • 24. Algorithmic Intelligence Lab • Multiple choice learning (MCL) [Guzman’ 12] • Making each model specialized for certain subset of data • Overconfidence issues of MCL Ensemble Methods for Deep Neural Networks 24 Cat Cat Model 1 (specialized in “Cat” image) Model 2 (specialized in “Dog” image)Dog Dog Cat Overconfident 1% 99% 97% 3%
  • 25. Algorithmic Intelligence Lab • Multiple choice learning (MCL) [Guzman’ 12] • Making each model specialized for certain subset of data • Overconfidence issues of MCL Ensemble Methods for Deep Neural Networks 25 Cat Cat Model 1 (specialized in “Cat” image) Model 2 (specialized in “Dog” image)Dog Dog Cat 1% 99% 97% 3% DogCat 49% 51% Averaged probability Average Voting
  • 26. Algorithmic Intelligence Lab • Making the specialized models with confident predictions • Main components of our contributions • Experiments on CIFAR-10 using 5 CNNs (2 Conv + 2 FC) Confident Multiple Choice Learning (CMCL) 26 New loss: confident oracle loss New architecture: feature sharing New training method: random labeling
  • 27. Algorithmic Intelligence Lab • Confident oracle loss • Generating confident predictions by minimizing the KL divergence Confident Oracle Loss 27
  • 28. Algorithmic Intelligence Lab • Confident oracle loss • Generating confident predictions by minimizing the KL divergence Confident Oracle Loss 28 Model 1 Model 2 Model 3 Data distribution
  • 29. Algorithmic Intelligence Lab • Confident oracle loss • Generating confident predictions by minimizing the KL divergence Confident Oracle Loss 29 Model 1 Model 2 Model 3 Data distribution Uniform distribution
  • 30. Algorithmic Intelligence Lab • Classification test set error rates on CIFAR-10 and SVHN • Top-1 error • Select the class from averaged probability • Oracle error • Measuring whether none of the members predict the correct class • We use both feature sharing and random labeling for all experiments Experimental Results: Image Classification 30 • 32 × 32 RGB • 10 classes • 50,000 training set • 10,000 test set • 32 × 32 RGB • 10 classes • 73,257 training set • 26,032 test set CIFAR-10 [Krizhevsky’ 09] SVHN [Netzer’ 11]
  • 31. Algorithmic Intelligence Lab • Ensemble of small-scale CNNs (2 Conv + 2 FC) Experimental Results: Image Classification 31 K=1 K=2 Model 1 Model 2 Model 3 Model 1 Model 2 Model 3 “Picking K specialized models”
  • 32. Algorithmic Intelligence Lab • Ensemble of small-scale CNNs (2 Conv + 2 FC) • Ensemble of 5 large-scale CNNs Experimental Results: Image Classification 32
  • 33. Algorithmic Intelligence Lab • iCoseg dataset Experimental Results: Image Segmentation 33 Fully convolutional neural networks (FCNs) [Long’ 15] Pixel-level classification problem with 2 classes 1(foreground) and 0 (background) [Long’ 15] Long, J., Shelhamer, E. and Darrell, T. Fully convolutional networks for semantic segmentation. In CVPR, 2015.
  • 34. Algorithmic Intelligence Lab • Prediction results of segmentation for few sample images • MCL and CMCL generate high-quality predictions • CMCL only outperforms IE in terms of the top-1 error Experimental Results: Image Segmentation 34 - 6.77% relative reduction
  • 35. Algorithmic Intelligence Lab Outline • Introduction • Predictive uncertainty of deep neural networks • Summary • How to train confident neural networks • Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution Samples [Lee’ 18a] • Applications • Confident Multiple Choice Learning [Lee’ 17] • Hierarchical novelty detection [Lee’ 18b] • Conclusion 35 [Lee’ 18a] Lee, K., Lee, H., Lee, K. and Shin, J. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. I n ICLR, 2018. [Lee’ 17] Lee, K., Hwang, C., Park, K. and Shin, J. Confident Multiple Choice Learning. In ICML, 2017. [Lee’ 18b] Lee, K., Lee, Min. K, Zhang, Y. Shin. J, Lee, H. Hierarchical Novelty Detection for Visual Object Recognition, In CVPR, 2018.
  • 36. Algorithmic Intelligence Lab • Objective • 1. Find the closest known (super-)category in taxonomy • 2. Find fine-grained classification for novel categories (i.e., out-of- distribution samples) Hierarchical Novelty Detection 36 Figure 1. An illustration of our hierarchical novelty detection task
  • 37. Algorithmic Intelligence Lab • Top-down method (TD) • p(child) = ∑super p(child | super) p(super) • Objective • Inference • Definition of confidence: Two Main Approaches 37 Novel class
  • 38. Algorithmic Intelligence Lab • ImageNet dataset • 22K classes • Taxonomy • 396 super classes of 1K known leaf classes • Rest of 21K classes can be used as novel class • Example Experimental Results on ImageNet Dataset 38 [Deng’ 12] J. Deng, J. Krause, A. C. Berg, and L. Fei-Fei. Hedging your bets: Optimizing accuracy-specificity trade offs in large scale visual recognition. In CVPR , pages 3450–3457. IEEE, 2012. • Hierarchical novelty detection performance • Baseline: DARTS [Deng’ 12] • One can note that our methods have higher novel class accuracy than DARTS to have a same known class accuracy in most regions
  • 39. Algorithmic Intelligence Lab • We propose a new method for training confident deep neural networks • It produce the uniform distribution when the input is not from target distribution • We show that it can be applied to many machine learning problems: • Detecting out-of-distribution problem • Ensemble learning using deep neural networks • Hierarchical novelty detection • We believe that our new approach brings a refreshing angle for developing confident deep networks in many related applications: • Network calibration • Adversarial example detection • Bayesian probabilistic models • Semi-supervised learning Conclusion 39