The document discusses approaches for using deep learning with small datasets, including transfer learning techniques like fine-tuning pre-trained models, multi-task learning, and metric learning approaches for few-shot and zero-shot learning problems. It also covers domain adaptation techniques when labels are not available, as well as anomaly detection for skewed label distributions. Traditional models like SVM are suggested as initial approaches, with deep learning techniques applied if those are not satisfactory.
DetectoRS for Object Detection/Segmentation
On COCO test-dev, DetectoRS achieves state-of-the art 55.7% box AP for object detection, 48.5% mask AP for instance segmentation, and 50.0% PQ for panoptic segmentation.
(2020.07)
Learning from Simulated and Unsupervised Images through Adversarial Training....eraser Juan José Calderón
Learning from Simulated and Unsupervised Images through Adversarial Training
Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb
Apple Inc.
{a_shrivastava, tpf, otuzel, jsusskind, wenda_wang, rwebb}@apple.com
DetectoRS for Object Detection/Segmentation
On COCO test-dev, DetectoRS achieves state-of-the art 55.7% box AP for object detection, 48.5% mask AP for instance segmentation, and 50.0% PQ for panoptic segmentation.
(2020.07)
Learning from Simulated and Unsupervised Images through Adversarial Training....eraser Juan José Calderón
Learning from Simulated and Unsupervised Images through Adversarial Training
Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb
Apple Inc.
{a_shrivastava, tpf, otuzel, jsusskind, wenda_wang, rwebb}@apple.com
Using Optimal Learning to Tune Deep Learning PipelinesScott Clark
SigOpt talk from NVIDIA GTC 2017 and AWS Popup Loft AI Day
We'll introduce Bayesian optimization as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time consuming or expensive. Deep learning pipelines are notoriously expensive to train and often have many tunable parameters, including hyperparameters, the architecture, and feature transformations, that can have a large impact on the efficacy of the model. We'll provide several example applications using multiple open source deep learning frameworks and open datasets. We'll compare the results of Bayesian optimization to standard techniques like grid search, random search, and expert tuning. Additionally, we'll present a robust benchmark suite for comparing these methods in general.
Building a Tensorflow-based model that extracts the "best" frames from a video, which are then used as auto-generated thumbnails and thumbstrips. We used transfer learning on Google's Inceptionv3 model, which was pretrained with ImageNet data and retrained on JW Player's thumbnail library.
How to use transfer learning to bootstrap image classification and question a...Wee Hyong Tok
#theaiconf SFO 2018
Session by Danielle Dean, WeeHyong Tok
Transfer learning enables you to use pretrained deep neural networks trained on various large datasets (ImageNet, CIFAR, WikiQA, SQUAD, and more) and adapt them for various deep learning tasks (e.g., image classification, question answering, and more).
Wee Hyong Tok and Danielle Dean share the basics of transfer learning and demonstrate how to use the technique to bootstrap the building of custom image classifiers and custom question-answering (QA) models. You’ll learn how to use the pretrained CNNs available in various model libraries to custom build a convolution neural network for your use case. In addition, you’ll discover how to use transfer learning for question-answering tasks, with models trained on large QA datasets (WikiQA, SQUAD, and more), and adapt them for new question-answering tasks.
https://conferences.oreilly.com/artificial-intelligence/ai-ca/public/schedule/detail/68527
Mariia Havrylovych "Active learning and weak supervision in NLP projects"Fwdays
Successful artificial intelligence solutions always require a massive amount of high-quality labeled data. In most cases, we don’t have a large and qualitative labeled set together. Weak supervision and active learning tools may help you optimize the labeling process and address the shortage of data labels.
First, we will review how active learning can significantly reduce the amount of labeled data for training with classic approaches. We will show how active learning methods can be customized for a specific (NLP) task by using text embedding.
With weak supervision, we will see how using simple rules gets a big train dataset automatically and high model performance without manual labeling at all.
In the end, we will combine active learning and weak supervision by taking advantage of both techniques and achieving the best metrics.
Slides used during the virtual conference, NetCoreConf on April 04, 2020. The session was a introduction to Machine Learning for .Net developers, using ML.Net as the main framework.
Certification Study Group - NLP & Recommendation Systems on GCP Session 5gdgsurrey
This session features Raghavendra Guttur's exploration of "Atlas," a chatbot powered by Llama2-7b with MiniLM v2 enhancements for IT support. ChengCheng Tan will discuss ML pipeline automation, monitoring, optimization, and maintenance.
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto MLBruno Capuano
Slides used during the "Machine Learning Galore" session, on 2019 December 19 at the Microsoft offices. Event hosted by the Mississauga .Net User Group and my session was around Machine Learning.Net and Auto ML
Using Optimal Learning to Tune Deep Learning PipelinesScott Clark
SigOpt talk from NVIDIA GTC 2017 and AWS Popup Loft AI Day
We'll introduce Bayesian optimization as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time consuming or expensive. Deep learning pipelines are notoriously expensive to train and often have many tunable parameters, including hyperparameters, the architecture, and feature transformations, that can have a large impact on the efficacy of the model. We'll provide several example applications using multiple open source deep learning frameworks and open datasets. We'll compare the results of Bayesian optimization to standard techniques like grid search, random search, and expert tuning. Additionally, we'll present a robust benchmark suite for comparing these methods in general.
Building a Tensorflow-based model that extracts the "best" frames from a video, which are then used as auto-generated thumbnails and thumbstrips. We used transfer learning on Google's Inceptionv3 model, which was pretrained with ImageNet data and retrained on JW Player's thumbnail library.
How to use transfer learning to bootstrap image classification and question a...Wee Hyong Tok
#theaiconf SFO 2018
Session by Danielle Dean, WeeHyong Tok
Transfer learning enables you to use pretrained deep neural networks trained on various large datasets (ImageNet, CIFAR, WikiQA, SQUAD, and more) and adapt them for various deep learning tasks (e.g., image classification, question answering, and more).
Wee Hyong Tok and Danielle Dean share the basics of transfer learning and demonstrate how to use the technique to bootstrap the building of custom image classifiers and custom question-answering (QA) models. You’ll learn how to use the pretrained CNNs available in various model libraries to custom build a convolution neural network for your use case. In addition, you’ll discover how to use transfer learning for question-answering tasks, with models trained on large QA datasets (WikiQA, SQUAD, and more), and adapt them for new question-answering tasks.
https://conferences.oreilly.com/artificial-intelligence/ai-ca/public/schedule/detail/68527
Mariia Havrylovych "Active learning and weak supervision in NLP projects"Fwdays
Successful artificial intelligence solutions always require a massive amount of high-quality labeled data. In most cases, we don’t have a large and qualitative labeled set together. Weak supervision and active learning tools may help you optimize the labeling process and address the shortage of data labels.
First, we will review how active learning can significantly reduce the amount of labeled data for training with classic approaches. We will show how active learning methods can be customized for a specific (NLP) task by using text embedding.
With weak supervision, we will see how using simple rules gets a big train dataset automatically and high model performance without manual labeling at all.
In the end, we will combine active learning and weak supervision by taking advantage of both techniques and achieving the best metrics.
Slides used during the virtual conference, NetCoreConf on April 04, 2020. The session was a introduction to Machine Learning for .Net developers, using ML.Net as the main framework.
Certification Study Group - NLP & Recommendation Systems on GCP Session 5gdgsurrey
This session features Raghavendra Guttur's exploration of "Atlas," a chatbot powered by Llama2-7b with MiniLM v2 enhancements for IT support. ChengCheng Tan will discuss ML pipeline automation, monitoring, optimization, and maintenance.
2019 12 19 Mississauga .Net User Group - Machine Learning.Net and Auto MLBruno Capuano
Slides used during the "Machine Learning Galore" session, on 2019 December 19 at the Microsoft offices. Event hosted by the Mississauga .Net User Group and my session was around Machine Learning.Net and Auto ML
Knowledge graphs generation is outpacing the ability to intelligently use the information that they contain. Octavian's work is pioneering Graph Artificial Intelligence to provide the brains to make knowledge graphs useful.
Our neural networks can take questions and knowledge graphs and return answers. Imagine:
a google assistant that reads your own knowledge graph (and actually works)
a BI tool reads your business' knowledge graph
a legal assistant that reads the graph of your case
Taking a neural network approach is important because neural networks deal better with the noise in data and variety in schema. Using neural networks allows people to ask questions of the knowledge graph in their own words, not via code or query languages.
Octavian's approach is to develop neural networks that can learn to manipulate graph knowledge into answers. This approach is radically different to using networks to generate graph embeddings. We believe this approach could transform how we interact with databases.
The Frontier of Deep Learning in 2020 and BeyondNUS-ISS
This talk will be a summary of the recent advances in deep learning research, current trends in the industry, and the opportunities that lie ahead.
We will discuss topics in research such as:
Transformers, GPT-3, BERT
Neural Architecture Search, Evolutionary Search
Distillation, self-learning
NeRF
Self-Attention
Also shifting industry trends such as:
The move to free data
Rising importance of 3D vision
Using synthetic data (Sim2Real)
Mobile vision & Federated Learning
Transfer learning enables you to use pretrained deep neural networks trained on various large datasets (ImageNet, CIFAR, WikiQA, SQUAD, and more) and adapt them for various deep learning tasks (e.g., image classification, question answering, and more).
Wee Hyong Tok and Danielle Dean share the basics of transfer learning and demonstrate how to use the technique to bootstrap the building of custom image classifiers and custom question-answering (QA) models. You’ll learn how to use the pretrained CNNs available in various model libraries to custom build a convolution neural network for your use case. In addition, you’ll discover how to use transfer learning for question-answering tasks, with models trained on large QA datasets (WikiQA, SQUAD, and more), and adapt them for new question-answering tasks.
Topics include:
An introduction to convolution neural networks and question-answering problems
Using pretrained CNNs and the last fully connected layer as a featurizer (Once the features are extracted, any existing classifier can be used for image classification, using the extracted features as inputs.)
Fine-tuning the pretrained models and adapting them for the new images
Using pretrained QA models trained on large QA datasets (WikiQA, SQUAD) and applying transfer learning for QA tasks
Show drafts
volume_up
Empowering the Data Analytics Ecosystem: A Laser Focus on Value
The data analytics ecosystem thrives when every component functions at its peak, unlocking the true potential of data. Here's a laser focus on key areas for an empowered ecosystem:
1. Democratize Access, Not Data:
Granular Access Controls: Provide users with self-service tools tailored to their specific needs, preventing data overload and misuse.
Data Catalogs: Implement robust data catalogs for easy discovery and understanding of available data sources.
2. Foster Collaboration with Clear Roles:
Data Mesh Architecture: Break down data silos by creating a distributed data ownership model with clear ownership and responsibilities.
Collaborative Workspaces: Utilize interactive platforms where data scientists, analysts, and domain experts can work seamlessly together.
3. Leverage Advanced Analytics Strategically:
AI-powered Automation: Automate repetitive tasks like data cleaning and feature engineering, freeing up data talent for higher-level analysis.
Right-Tool Selection: Strategically choose the most effective advanced analytics techniques (e.g., AI, ML) based on specific business problems.
4. Prioritize Data Quality with Automation:
Automated Data Validation: Implement automated data quality checks to identify and rectify errors at the source, minimizing downstream issues.
Data Lineage Tracking: Track the flow of data throughout the ecosystem, ensuring transparency and facilitating root cause analysis for errors.
5. Cultivate a Data-Driven Mindset:
Metrics-Driven Performance Management: Align KPIs and performance metrics with data-driven insights to ensure actionable decision making.
Data Storytelling Workshops: Equip stakeholders with the skills to translate complex data findings into compelling narratives that drive action.
Benefits of a Precise Ecosystem:
Sharpened Focus: Precise access and clear roles ensure everyone works with the most relevant data, maximizing efficiency.
Actionable Insights: Strategic analytics and automated quality checks lead to more reliable and actionable data insights.
Continuous Improvement: Data-driven performance management fosters a culture of learning and continuous improvement.
Sustainable Growth: Empowered by data, organizations can make informed decisions to drive sustainable growth and innovation.
By focusing on these precise actions, organizations can create an empowered data analytics ecosystem that delivers real value by driving data-driven decisions and maximizing the return on their data investment.
Techniques to optimize the pagerank algorithm usually fall in two categories. One is to try reducing the work per iteration, and the other is to try reducing the number of iterations. These goals are often at odds with one another. Skipping computation on vertices which have already converged has the potential to save iteration time. Skipping in-identical vertices, with the same in-links, helps reduce duplicate computations and thus could help reduce iteration time. Road networks often have chains which can be short-circuited before pagerank computation to improve performance. Final ranks of chain nodes can be easily calculated. This could reduce both the iteration time, and the number of iterations. If a graph has no dangling nodes, pagerank of each strongly connected component can be computed in topological order. This could help reduce the iteration time, no. of iterations, and also enable multi-iteration concurrency in pagerank computation. The combination of all of the above methods is the STICD algorithm. [sticd] For dynamic graphs, unchanged components whose ranks are unaffected can be skipped altogether.
Opendatabay - Open Data Marketplace.pptxOpendatabay
Opendatabay.com unlocks the power of data for everyone. Open Data Marketplace fosters a collaborative hub for data enthusiasts to explore, share, and contribute to a vast collection of datasets.
First ever open hub for data enthusiasts to collaborate and innovate. A platform to explore, share, and contribute to a vast collection of datasets. Through robust quality control and innovative technologies like blockchain verification, opendatabay ensures the authenticity and reliability of datasets, empowering users to make data-driven decisions with confidence. Leverage cutting-edge AI technologies to enhance the data exploration, analysis, and discovery experience.
From intelligent search and recommendations to automated data productisation and quotation, Opendatabay AI-driven features streamline the data workflow. Finding the data you need shouldn't be a complex. Opendatabay simplifies the data acquisition process with an intuitive interface and robust search tools. Effortlessly explore, discover, and access the data you need, allowing you to focus on extracting valuable insights. Opendatabay breaks new ground with a dedicated, AI-generated, synthetic datasets.
Leverage these privacy-preserving datasets for training and testing AI models without compromising sensitive information. Opendatabay prioritizes transparency by providing detailed metadata, provenance information, and usage guidelines for each dataset, ensuring users have a comprehensive understanding of the data they're working with. By leveraging a powerful combination of distributed ledger technology and rigorous third-party audits Opendatabay ensures the authenticity and reliability of every dataset. Security is at the core of Opendatabay. Marketplace implements stringent security measures, including encryption, access controls, and regular vulnerability assessments, to safeguard your data and protect your privacy.
Explore our comprehensive data analysis project presentation on predicting product ad campaign performance. Learn how data-driven insights can optimize your marketing strategies and enhance campaign effectiveness. Perfect for professionals and students looking to understand the power of data analysis in advertising. for more details visit: https://bostoninstituteofanalytics.org/data-science-and-artificial-intelligence/
Adjusting primitives for graph : SHORT REPORT / NOTESSubhajit Sahu
Graph algorithms, like PageRank Compressed Sparse Row (CSR) is an adjacency-list based graph representation that is
Multiply with different modes (map)
1. Performance of sequential execution based vs OpenMP based vector multiply.
2. Comparing various launch configs for CUDA based vector multiply.
Sum with different storage types (reduce)
1. Performance of vector element sum using float vs bfloat16 as the storage type.
Sum with different modes (reduce)
1. Performance of sequential execution based vs OpenMP based vector element sum.
2. Performance of memcpy vs in-place based CUDA based vector element sum.
3. Comparing various launch configs for CUDA based vector element sum (memcpy).
4. Comparing various launch configs for CUDA based vector element sum (in-place).
Sum with in-place strategies of CUDA mode (reduce)
1. Comparing various launch configs for CUDA based vector element sum (in-place).
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
5. Before do Something Fancy
http://blog.kaggle.com/2017/01/05/your-year-on-kaggle-most-memorable-
community-stats-from-2016/
on deep learning
1. Traditional Model
6. Before do Something Fancy
SVM 은 MDA, Logit, CBR 과 비교해서 우수한 예측력을 보였으며 .... 인공신경망과 비
슷한 수준의 높은 예측력을 나타낼 뿐만 아니라 인공신경망의 한계점으로 지적되었던
과대 적합, 국소 최적화와 같은 한계점들을 완화하는 장점을 가진다. (2003 한인구)
http://www.aistudy.co.kr/pattern/support_vector_machine.htm
https://www.researchgate.net/post/Which_classifier_is_the_better_in_case_of_small_data_s
amples
그냥 일단 먼저 다른 모델(SVM) 돌려보세요...
on deep learning
1. Traditional Model
7. Before do Something Fancy on deep learning
2. Data Augmentation
For Image
https://github.com/aleju/imgaug
For Audio
https://github.com/bmcfee/muda
For others
put some money
8. Wait... Why Deep Learning?
https://www.quora.com/Why-is-xgboost-given-so-much-less-attention-than-deep-
learning-despite-its-ubiquity-in-winning-Kaggle-solutions
When you do have "enough" training data, and when somehow you manage to
find the matching magical deep architecture, deep learning blows away any other
method by a large margin.
Will you still do it?
9.
10. How can we train with
few data
Dive with Example, no math required!
ETRI 두스 2018 _ 2차 스터디
davinnovation@gmail.com
In deep learning perspective
12. 후에 소개되는 방법론들이
앞에서 설명한 결과보다 좋아진다는 보장은 없음!!!
It’s just the other tools. Not magic wand
13. Approaches
if (data size is small) and not (satisfied SVM):
if (sufficient label):
Fine Tuning
elif (few labels):
N-shot Learning
elif (no labels):
Zero-shot Learning/Domain Adaptation
elif (skewed labels):
Anomaly Detection if special else Training Tricks!
else:
Hire Alba for labeling!
else:
if !(sufficient label):
semi-supervised learning, unsupervised learning
else:
JUST DO DEEP LEARNING!
14. Approaches
if (data size is small) and not (satisfied SVM):
if (sufficient label):
Fine Tuning
elif (few labels):
N-shot Learning
elif (no labels):
Zero-shot Learning/Domain Adaptation
elif (skewed labels):
Anomaly Detection if special else Training Tricks!
else:
Hire Alba for labeling!
else:
if !(sufficient label):
semi-supervised learning, unsupervised learning
else:
JUST DO DEEP LEARNING!
Transfer
Learning
Uncertainty
Learning Method
15. Transfer Learning
== Knowledge transfer
Pan, Sinno Jialin, and Qiang Yang. "A survey on transfer learning." IEEE Transactions on knowledge and data
engineering 22.10 (2010): 1345-1359.
Before we dive into models...
20. Transfer Learning
== Knowledge transfer
Transfer Types
Instance-transfer re-weight (source-data trained)model by target-data
== min(model(source)) -> min(model(target))
Feature-representation
transfer
find good feature representation for source & target
== min ( model_feature(source).variation - model_feature(target).variation )
Parameter-transfer discover share parameter between source & target
== 1/2 ( model_feature(source).weight + model_feature(target).weight )
Relational-knowledge-
transfer
build mapping of relational knowledge between source & target
learn source - > learn target
learn source & target same time
model weight perspective...
learn some relational info
21. FINE TUNING
if (sufficient label)
if (data size is small) and not (satisfied SVM):
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
10M > datasets
Fixed Feature Extractor
Fine-tuning
In deep learning perspective with small data
http://cs231n.github.io/transfer-learning/
22. FINE TUNING
if (sufficient label)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
SC : Sparse Coding ( Scratch )
TF : Transfer Learning
CTL : Complete TL
PTL : Partial TL
MTL : Multi-task TL
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7480825 http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7064414
16220 images
23. FINE TUNING
if (sufficient label)
if (data size is small) and not (satisfied SVM):
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
10M > datasets
https://arxiv.org/pdf/1311.2901v3.pdf
each layer can extract Features
Why fine-tune can work on deep learning
In deep learning perspective with small data
24. FINE TUNING
if (sufficient label)
if (data size is small) and not (satisfied SVM):
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
10M > datasets
https://arxiv.org/pdf/1411.1792.pdf
How much we fine tune?
In deep learning perspective with small data
25. Multi-task learning
if (sufficient label)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
https://openreview.net/pdf?id=S1PWi_lC-
70,000
70,000
70,000
26. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar )
Human Deep Learning
27. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar )
single one picture book 60,000 train data (MNIST)
( Actually is NOT! but just for fun...)
28. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar ) Meta-Learning
Meta Learning
Learning to Learn
http://bair.berkeley.edu/blog/2017/07/18/lear
ning-to-learn/
29. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar ) Memory model ( Neural Turing Machine )
RNN Memory
https://www.slideshare.net/ssuserafc864/one-shot-learning-deep-learning-
meta-learn
30. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar ) Memory model ( Neural Turing Machine )
One-shot Learn with Meta
https://arxiv.org/pdf/1605.06065.pdf
Omniglot Dataset : 1600 > classes
1200 class train, 423 class test ( downscale to 20x20 )
+ plus rotate augmentation
31. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar ) Metric Learning Perspective
Metric Learning : learns Feature Extract + Features Manifold
https://drive.google.com/file/d/1kDedrnO4N2l9RATSXRS0FuAZqW1mHPWu/view
Metric Learning
32. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar ) Metric Learning Perspective
https://drive.google.com/file/d/1kDedrnO4N2l9RATSXRS0FuAZqW1mHPWu/view
Metric Learning
33. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar ) Metric Learning Perspective
https://drive.google.com/file/d/1kDedrnO4N2l9RATSXRS0FuAZqW1mHPWu/view
One-Shot Learn with metric
60, 000 color images of size 84 × 84 with 100 classes
NOT LEARN CLASS
LEARNS metrics
https://arxiv.org/pdf/1606.04080.pdf
34. N-Shot
elif (few labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
N-Shot ( One shot is more familiar ) Metric Learning Perspective
https://drive.google.com/file/d/1kDedrnO4N2l9RATSXRS0FuAZqW1mHPWu/view
One-Shot Learn with metric
35. Zero-Shot
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
Zero-shot Metric Learning Perspective
https://drive.google.com/file/d/1kDedrnO4N2l9RATSXRS0FuAZqW1mHPWu/view
Zero-shot Learn with metric
36. Zero-Shot
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
Zero-shot Metric Learning Perspective
https://drive.google.com/file/d/1kDedrnO4N2l9RATSXRS0FuAZqW1mHPWu/view
Zero-shot Learn with metric
37. Domain Adaptation
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
No Domain
Adaptation
38. Domain Adaptation
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
Class = Backpack
Amazon
DSLR
Webcam
Caltech
Training
39. Domain Adaptation
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
Domain-Adversarial Neural Network
Classifier의 성능을 유지하면서
(Classifier)
source || target feature 분포도 고려,
Source에서 왔는지 Target에서 왔는지 알
수 없도록 방해
(GAN)
40. Domain Adaptation
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
Domain-Adversarial Neural Network
41. Domain Adaptation
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
Domain Separation Networks
이미지 복원값
shared encoder와 차이classification loss
2개 difference를 비슷하게 만들어줌
42. Domain Adaptation
elif (no labels)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
Domain Separation Networks
Source-only : Training with only source data
Target-only : Training with only Target data Testing on target data
SVHN
GTSRBMNIST
43. Anomaly Detection (Novelty Detection)
elif (skewed labels) and (special case)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
https://www.youtube.com/watch?v=hHHmWmJG9Rw
It’s look like Zero – shot learn
44. Anomaly Detection (Novelty Detection)
elif (skewed labels) and (special case)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
https://www.datascience.com/blog/python-
anomaly-detection
Gaussian Distribution -> Check Uncertainty!!!
45. Anomaly Detection (Novelty Detection)
elif (skewed labels) and (special case)
if (data size is small) and not (satisfied SVM):
In deep learning perspective with small data
safe visual navigation via deep learning https://www.slideshare.net/samchoi7/modeling-uncertainty-in-deep-learning
46. Training Skills
elif (skewed labels)
if (data size is small) and not (satisfied SVM):
Model weight update with balance
https://arxiv.org/pdf/1710.05381.pdf : imbalance class effect
Stratified Sampling / Bootstrapping... / K-Fold...