SlideShare a Scribd company logo
ARCHITECTURAL CONDITIONING
FOR DISENTANGLEMENT OF OBJECT
IDENTITY AND POSTURE INFORMATION
저자 : Kazutoshi Sagi, Takahiro Toizumi & Yuzo Senda
Data Science Research Laboratories
NEC Corporation
https://openreview.net/forum?id=HkaYjG6Lf
정리 : 김홍배
일반적으로 다양한 pose에 대한 image를 획득하여 Networks을
Pose에 대하여 Invariance하게 Training  High cost approach
3D Object Identification Problem
Equivariance
Φ
Image(X)
Latent(Z) Z1 Z2
𝑇𝑔
2
𝑇𝑔
1
Φ
Transformation
X1 X2
Z2 = 𝑻 𝒈
𝟐
Z1 = 𝑻 𝒈
𝟐
Φ(X1) = Φ(𝑻 𝒈
𝟏
X1 )
: Invariance is special case of equivariance where 𝑇𝑔
2 is the identity.
X2 = 𝑇𝑔
1
X1
Z2 = 𝑇𝑔
2
Z1
: 주어진 Image의 pose변환에 대하여 Latent space상에서
명확한 변환관계를 찾을 수 있다면 ?
Z1 ≠ Z2 but keeps the relationship
Mapping
ft’n(Φ(·))
ROLLABLE LATENT SPACE
0
1
2
3
4
5
6
7
8
9
10
11
0 1 2 3 4 5 6 7 8 9 10 11
0
1
2
3
4
5
6
7
8
9
10
11
Image Latent vector
Shift by
circular permutation
Angular
rotation
본 연구에서 제시한 아이디어
3 4 5 6 7 8 9 10 11 0 1 2
𝑋θ 𝑖
𝑋θ 𝑗
𝑍θ 𝑖
𝑍θ 𝑗
ROLLABLE LATENT SPACE
Image space에서의 pose 변경(Angular rotation)이 Latent vector의
Circular Permutation에 의한 Shift로 나타낼 수 있다면 ?
 2 space의 Mapping 관계를 명확하게 알 수 있으며
Training하지않은 다른 pose에서의 latent vector를 유추할 수 있다 !
 여기서는 Auto-Encoder를 살짝 바꿔서 강제로 학습을 시킨다
ROLLABLE LATENT SPACE
𝑋θ 𝑖
𝑋θ 𝑗
𝑍θ 𝑖
𝑍θ 𝑗
여기서 Roll(Z, s)는 𝑍θ 𝑖
를 shift parameter s(각도 차) 만큼 Cyclic
permutation 시킨 후 Decoder쪽의 입력 latent vector로 준다.
Encoder쪽 입력에 𝑋θ 𝑖
를 Decoder 쪽 출력에는 회전한 𝑋θ 𝑗
를 준다.
ROLLABLE LATENT SPACE
𝑋θ 𝑖
𝑋θ 𝑗
𝑍θ 𝑖
𝑍θ 𝑗
Decoder의 출력이 𝑋θ 𝑗
와 근사하도록 Networks을 훈련시키면 됨.
Feature Augmentation by RLS
Classifier의 훈련 시 Image level에서의 augmentation이 필요없이 주어
진 image, 𝑋𝑖의 latent vector, 𝑍𝑖를 랜덤하게 shift 시킴으로서 Feature
level에서의 augmentation이 가능
EXPERIMENTAL RESULTS
- The encoder and the decoder just consist of one hidden fully connected
layer with ReLU activation for each.
- The number of the latent space dimentions is given as 24, which
corresponds to 2 dimensions in 12 viewing directions
Exp. 1 : DISENTANGLING 2D IMAGE ROTATION
Reconstructions of the test dataset. An input and reconstructions in given
rotation angles generated by
are presented from the left column of each row.
EXPERIMENTAL RESULTS
Exp. 2 : DISENTANGLING 3D OBJECT ROTATION
• 809 chair models are selected
• The first 500 models are used as a training set and the remaining 309 models
are used as a test set.
• Each chair model is rendered from 31 azimuth angles and 2 elevation angles
(20 and 30)
• A deep convolutional encoder-decoder architecture are used.
• The number of the latent space dimensions is given as 992, which corresponds
to 32 dimensions in 31 viewing directions.
EXPERIMENTAL RESULTS
Exp. 2 : DISENTANGLING 3D OBJECT ROTATION
(a): A network architecture used in the experiment of 3D object rotation.
(b): Reconstructions of the test dataset. An input and reconstructions in given
rotation angles are shown from the left column of each row.

More Related Content

What's hot

Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Universitat Politècnica de Catalunya
 
Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)
Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)
Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)
Universitat Politècnica de Catalunya
 
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
Universitat Politècnica de Catalunya
 
Variational Autoencoders For Image Generation
Variational Autoencoders For Image GenerationVariational Autoencoders For Image Generation
Variational Autoencoders For Image Generation
Jason Anderson
 
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Universitat Politècnica de Catalunya
 
Variational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math BehindVariational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math Behind
Varun Reddy
 
Backpropagation - Elisa Sayrol - UPC Barcelona 2018
Backpropagation - Elisa Sayrol - UPC Barcelona 2018Backpropagation - Elisa Sayrol - UPC Barcelona 2018
Backpropagation - Elisa Sayrol - UPC Barcelona 2018
Universitat Politècnica de Catalunya
 
Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)
Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)
Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)
Universitat Politècnica de Catalunya
 
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
Universitat Politècnica de Catalunya
 
Rabbit challenge 3 DNN Day2
Rabbit challenge 3 DNN Day2Rabbit challenge 3 DNN Day2
Rabbit challenge 3 DNN Day2
TOMMYLINK1
 
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Universitat Politècnica de Catalunya
 
The Perceptron (D1L2 Deep Learning for Speech and Language)
The Perceptron (D1L2 Deep Learning for Speech and Language)The Perceptron (D1L2 Deep Learning for Speech and Language)
The Perceptron (D1L2 Deep Learning for Speech and Language)
Universitat Politècnica de Catalunya
 
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
Masahiro Suzuki
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Universitat Politècnica de Catalunya
 
Digital signal and image processing FAQ
Digital signal and image processing FAQDigital signal and image processing FAQ
Digital signal and image processing FAQ
Mukesh Tekwani
 
Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...
Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...
Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...
Universitat Politècnica de Catalunya
 
CS 354 Acceleration Structures
CS 354 Acceleration StructuresCS 354 Acceleration Structures
CS 354 Acceleration Structures
Mark Kilgard
 
00463517b1e90c1e63000000
00463517b1e90c1e6300000000463517b1e90c1e63000000
00463517b1e90c1e63000000Ivonne Liu
 
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Universitat Politècnica de Catalunya
 
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Universitat Politècnica de Catalunya
 

What's hot (20)

Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
 
Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)
Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)
Backpropagation (DLAI D3L1 2017 UPC Deep Learning for Artificial Intelligence)
 
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
The Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intelligence)
 
Variational Autoencoders For Image Generation
Variational Autoencoders For Image GenerationVariational Autoencoders For Image Generation
Variational Autoencoders For Image Generation
 
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
 
Variational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math BehindVariational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math Behind
 
Backpropagation - Elisa Sayrol - UPC Barcelona 2018
Backpropagation - Elisa Sayrol - UPC Barcelona 2018Backpropagation - Elisa Sayrol - UPC Barcelona 2018
Backpropagation - Elisa Sayrol - UPC Barcelona 2018
 
Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)
Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)
Attention Models (D3L6 2017 UPC Deep Learning for Computer Vision)
 
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
 
Rabbit challenge 3 DNN Day2
Rabbit challenge 3 DNN Day2Rabbit challenge 3 DNN Day2
Rabbit challenge 3 DNN Day2
 
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
Optimization for Neural Network Training - Veronica Vilaplana - UPC Barcelona...
 
The Perceptron (D1L2 Deep Learning for Speech and Language)
The Perceptron (D1L2 Deep Learning for Speech and Language)The Perceptron (D1L2 Deep Learning for Speech and Language)
The Perceptron (D1L2 Deep Learning for Speech and Language)
 
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
(研究会輪読) Facial Landmark Detection by Deep Multi-task Learning
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
 
Digital signal and image processing FAQ
Digital signal and image processing FAQDigital signal and image processing FAQ
Digital signal and image processing FAQ
 
Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...
Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...
Deep Generative Models II (DLAI D10L1 2017 UPC Deep Learning for Artificial I...
 
CS 354 Acceleration Structures
CS 354 Acceleration StructuresCS 354 Acceleration Structures
CS 354 Acceleration Structures
 
00463517b1e90c1e63000000
00463517b1e90c1e6300000000463517b1e90c1e63000000
00463517b1e90c1e63000000
 
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
 
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
 

Similar to ARCHITECTURAL CONDITIONING FOR DISENTANGLEMENT OF OBJECT IDENTITY AND POSTURE INFORMATION

A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth Estimation
Ryo Takahashi
 
TransNeRF
TransNeRFTransNeRF
TransNeRF
NavneetPaul2
 
PPT Image Analysis(IRDE, DRDO)
PPT Image Analysis(IRDE, DRDO)PPT Image Analysis(IRDE, DRDO)
PPT Image Analysis(IRDE, DRDO)Nidhi Gopal
 
Theories and Engineering Technics of 2D-to-3D Back-Projection Problem
Theories and Engineering Technics of 2D-to-3D Back-Projection ProblemTheories and Engineering Technics of 2D-to-3D Back-Projection Problem
Theories and Engineering Technics of 2D-to-3D Back-Projection Problem
Seongcheol Baek
 
20150703.journal club
20150703.journal club20150703.journal club
20150703.journal clubHayaru SHOUNO
 
Passive network-redesign-ntua
Passive network-redesign-ntuaPassive network-redesign-ntua
Passive network-redesign-ntua
IEEE NTUA SB
 
VoxelNet
VoxelNetVoxelNet
VoxelNet
taeseon ryu
 
Fisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingFisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous Driving
Yu Huang
 
Journey to structure from motion
Journey to structure from motionJourney to structure from motion
Journey to structure from motion
Ja-Keoung Koo
 
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...United States Air Force Academy
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNN
Chanuk Lim
 
AU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSE
AU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSEAU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSE
AU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSE
Thiyagarajan G
 
Yolo v2 ai_tech_20190421
Yolo v2 ai_tech_20190421Yolo v2 ai_tech_20190421
Yolo v2 ai_tech_20190421
穗碧 陳
 
Generating super resolution images using transformers
Generating super resolution images using transformersGenerating super resolution images using transformers
Generating super resolution images using transformers
NEERAJ BAGHEL
 
Weakly supervised semantic segmentation of 3D point cloud
Weakly supervised semantic segmentation of 3D point cloudWeakly supervised semantic segmentation of 3D point cloud
Weakly supervised semantic segmentation of 3D point cloud
Arithmer Inc.
 
I3602061067
I3602061067I3602061067
I3602061067
ijceronline
 
Computer vision 3 4
Computer vision 3 4Computer vision 3 4
Computer vision 3 4
sachinmore76
 
Isvc08
Isvc08Isvc08
Kccsi 2012 a real-time robust object tracking-v2
Kccsi 2012   a real-time robust object tracking-v2Kccsi 2012   a real-time robust object tracking-v2
Kccsi 2012 a real-time robust object tracking-v2
Prarinya Siritanawan
 
image_segmentation_ppt.pptx
image_segmentation_ppt.pptximage_segmentation_ppt.pptx
image_segmentation_ppt.pptx
fgdg12
 

Similar to ARCHITECTURAL CONDITIONING FOR DISENTANGLEMENT OF OBJECT IDENTITY AND POSTURE INFORMATION (20)

A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth Estimation
 
TransNeRF
TransNeRFTransNeRF
TransNeRF
 
PPT Image Analysis(IRDE, DRDO)
PPT Image Analysis(IRDE, DRDO)PPT Image Analysis(IRDE, DRDO)
PPT Image Analysis(IRDE, DRDO)
 
Theories and Engineering Technics of 2D-to-3D Back-Projection Problem
Theories and Engineering Technics of 2D-to-3D Back-Projection ProblemTheories and Engineering Technics of 2D-to-3D Back-Projection Problem
Theories and Engineering Technics of 2D-to-3D Back-Projection Problem
 
20150703.journal club
20150703.journal club20150703.journal club
20150703.journal club
 
Passive network-redesign-ntua
Passive network-redesign-ntuaPassive network-redesign-ntua
Passive network-redesign-ntua
 
VoxelNet
VoxelNetVoxelNet
VoxelNet
 
Fisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous DrivingFisheye Omnidirectional View in Autonomous Driving
Fisheye Omnidirectional View in Autonomous Driving
 
Journey to structure from motion
Journey to structure from motionJourney to structure from motion
Journey to structure from motion
 
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplica...
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNN
 
AU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSE
AU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSEAU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSE
AU QP Answer key NOv/Dec 2015 Computer Graphics 5 sem CSE
 
Yolo v2 ai_tech_20190421
Yolo v2 ai_tech_20190421Yolo v2 ai_tech_20190421
Yolo v2 ai_tech_20190421
 
Generating super resolution images using transformers
Generating super resolution images using transformersGenerating super resolution images using transformers
Generating super resolution images using transformers
 
Weakly supervised semantic segmentation of 3D point cloud
Weakly supervised semantic segmentation of 3D point cloudWeakly supervised semantic segmentation of 3D point cloud
Weakly supervised semantic segmentation of 3D point cloud
 
I3602061067
I3602061067I3602061067
I3602061067
 
Computer vision 3 4
Computer vision 3 4Computer vision 3 4
Computer vision 3 4
 
Isvc08
Isvc08Isvc08
Isvc08
 
Kccsi 2012 a real-time robust object tracking-v2
Kccsi 2012   a real-time robust object tracking-v2Kccsi 2012   a real-time robust object tracking-v2
Kccsi 2012 a real-time robust object tracking-v2
 
image_segmentation_ppt.pptx
image_segmentation_ppt.pptximage_segmentation_ppt.pptx
image_segmentation_ppt.pptx
 

More from 홍배 김

Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...
Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...
Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...
홍배 김
 
Gaussian processing
Gaussian processingGaussian processing
Gaussian processing
홍배 김
 
Lecture Summary : Camera Projection
Lecture Summary : Camera Projection Lecture Summary : Camera Projection
Lecture Summary : Camera Projection
홍배 김
 
Learning agile and dynamic motor skills for legged robots
Learning agile and dynamic motor skills for legged robotsLearning agile and dynamic motor skills for legged robots
Learning agile and dynamic motor skills for legged robots
홍배 김
 
Robotics of Quadruped Robot
Robotics of Quadruped RobotRobotics of Quadruped Robot
Robotics of Quadruped Robot
홍배 김
 
Basics of Robotics
Basics of RoboticsBasics of Robotics
Basics of Robotics
홍배 김
 
Recurrent Neural Net의 이론과 설명
Recurrent Neural Net의 이론과 설명Recurrent Neural Net의 이론과 설명
Recurrent Neural Net의 이론과 설명
홍배 김
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
홍배 김
 
Optimal real-time landing using DNN
Optimal real-time landing using DNNOptimal real-time landing using DNN
Optimal real-time landing using DNN
홍배 김
 
Anomaly Detection with GANs
Anomaly Detection with GANsAnomaly Detection with GANs
Anomaly Detection with GANs
홍배 김
 
Focal loss의 응용(Detection & Classification)
Focal loss의 응용(Detection & Classification)Focal loss의 응용(Detection & Classification)
Focal loss의 응용(Detection & Classification)
홍배 김
 
Convolution 종류 설명
Convolution 종류 설명Convolution 종류 설명
Convolution 종류 설명
홍배 김
 
Learning by association
Learning by associationLearning by association
Learning by association
홍배 김
 
알기쉬운 Variational autoencoder
알기쉬운 Variational autoencoder알기쉬운 Variational autoencoder
알기쉬운 Variational autoencoder
홍배 김
 
Binarized CNN on FPGA
Binarized CNN on FPGABinarized CNN on FPGA
Binarized CNN on FPGA
홍배 김
 
Visualizing data using t-SNE
Visualizing data using t-SNEVisualizing data using t-SNE
Visualizing data using t-SNE
홍배 김
 
Normalization 방법
Normalization 방법 Normalization 방법
Normalization 방법
홍배 김
 
Learning to remember rare events
Learning to remember rare eventsLearning to remember rare events
Learning to remember rare events
홍배 김
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
홍배 김
 
Meta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural NetworksMeta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural Networks
홍배 김
 

More from 홍배 김 (20)

Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...
Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...
Automatic Gain Tuning based on Gaussian Process Global Optimization (= Bayesi...
 
Gaussian processing
Gaussian processingGaussian processing
Gaussian processing
 
Lecture Summary : Camera Projection
Lecture Summary : Camera Projection Lecture Summary : Camera Projection
Lecture Summary : Camera Projection
 
Learning agile and dynamic motor skills for legged robots
Learning agile and dynamic motor skills for legged robotsLearning agile and dynamic motor skills for legged robots
Learning agile and dynamic motor skills for legged robots
 
Robotics of Quadruped Robot
Robotics of Quadruped RobotRobotics of Quadruped Robot
Robotics of Quadruped Robot
 
Basics of Robotics
Basics of RoboticsBasics of Robotics
Basics of Robotics
 
Recurrent Neural Net의 이론과 설명
Recurrent Neural Net의 이론과 설명Recurrent Neural Net의 이론과 설명
Recurrent Neural Net의 이론과 설명
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
 
Optimal real-time landing using DNN
Optimal real-time landing using DNNOptimal real-time landing using DNN
Optimal real-time landing using DNN
 
Anomaly Detection with GANs
Anomaly Detection with GANsAnomaly Detection with GANs
Anomaly Detection with GANs
 
Focal loss의 응용(Detection & Classification)
Focal loss의 응용(Detection & Classification)Focal loss의 응용(Detection & Classification)
Focal loss의 응용(Detection & Classification)
 
Convolution 종류 설명
Convolution 종류 설명Convolution 종류 설명
Convolution 종류 설명
 
Learning by association
Learning by associationLearning by association
Learning by association
 
알기쉬운 Variational autoencoder
알기쉬운 Variational autoencoder알기쉬운 Variational autoencoder
알기쉬운 Variational autoencoder
 
Binarized CNN on FPGA
Binarized CNN on FPGABinarized CNN on FPGA
Binarized CNN on FPGA
 
Visualizing data using t-SNE
Visualizing data using t-SNEVisualizing data using t-SNE
Visualizing data using t-SNE
 
Normalization 방법
Normalization 방법 Normalization 방법
Normalization 방법
 
Learning to remember rare events
Learning to remember rare eventsLearning to remember rare events
Learning to remember rare events
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
 
Meta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural NetworksMeta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural Networks
 

Recently uploaded

Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
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
 
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
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
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
 
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
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
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
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
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
 
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
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
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
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Tobias Schneck
 
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
 
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
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 

Recently uploaded (20)

Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
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
 
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...
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.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
 
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
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
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...
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
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
 
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...
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
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 ...
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
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
 
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
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 

ARCHITECTURAL CONDITIONING FOR DISENTANGLEMENT OF OBJECT IDENTITY AND POSTURE INFORMATION

  • 1. ARCHITECTURAL CONDITIONING FOR DISENTANGLEMENT OF OBJECT IDENTITY AND POSTURE INFORMATION 저자 : Kazutoshi Sagi, Takahiro Toizumi & Yuzo Senda Data Science Research Laboratories NEC Corporation https://openreview.net/forum?id=HkaYjG6Lf 정리 : 김홍배
  • 2. 일반적으로 다양한 pose에 대한 image를 획득하여 Networks을 Pose에 대하여 Invariance하게 Training  High cost approach 3D Object Identification Problem
  • 3. Equivariance Φ Image(X) Latent(Z) Z1 Z2 𝑇𝑔 2 𝑇𝑔 1 Φ Transformation X1 X2 Z2 = 𝑻 𝒈 𝟐 Z1 = 𝑻 𝒈 𝟐 Φ(X1) = Φ(𝑻 𝒈 𝟏 X1 ) : Invariance is special case of equivariance where 𝑇𝑔 2 is the identity. X2 = 𝑇𝑔 1 X1 Z2 = 𝑇𝑔 2 Z1 : 주어진 Image의 pose변환에 대하여 Latent space상에서 명확한 변환관계를 찾을 수 있다면 ? Z1 ≠ Z2 but keeps the relationship Mapping ft’n(Φ(·))
  • 4. ROLLABLE LATENT SPACE 0 1 2 3 4 5 6 7 8 9 10 11 0 1 2 3 4 5 6 7 8 9 10 11 0 1 2 3 4 5 6 7 8 9 10 11 Image Latent vector Shift by circular permutation Angular rotation 본 연구에서 제시한 아이디어 3 4 5 6 7 8 9 10 11 0 1 2 𝑋θ 𝑖 𝑋θ 𝑗 𝑍θ 𝑖 𝑍θ 𝑗
  • 5. ROLLABLE LATENT SPACE Image space에서의 pose 변경(Angular rotation)이 Latent vector의 Circular Permutation에 의한 Shift로 나타낼 수 있다면 ?  2 space의 Mapping 관계를 명확하게 알 수 있으며 Training하지않은 다른 pose에서의 latent vector를 유추할 수 있다 !  여기서는 Auto-Encoder를 살짝 바꿔서 강제로 학습을 시킨다
  • 6. ROLLABLE LATENT SPACE 𝑋θ 𝑖 𝑋θ 𝑗 𝑍θ 𝑖 𝑍θ 𝑗 여기서 Roll(Z, s)는 𝑍θ 𝑖 를 shift parameter s(각도 차) 만큼 Cyclic permutation 시킨 후 Decoder쪽의 입력 latent vector로 준다. Encoder쪽 입력에 𝑋θ 𝑖 를 Decoder 쪽 출력에는 회전한 𝑋θ 𝑗 를 준다.
  • 7. ROLLABLE LATENT SPACE 𝑋θ 𝑖 𝑋θ 𝑗 𝑍θ 𝑖 𝑍θ 𝑗 Decoder의 출력이 𝑋θ 𝑗 와 근사하도록 Networks을 훈련시키면 됨.
  • 8. Feature Augmentation by RLS Classifier의 훈련 시 Image level에서의 augmentation이 필요없이 주어 진 image, 𝑋𝑖의 latent vector, 𝑍𝑖를 랜덤하게 shift 시킴으로서 Feature level에서의 augmentation이 가능
  • 9. EXPERIMENTAL RESULTS - The encoder and the decoder just consist of one hidden fully connected layer with ReLU activation for each. - The number of the latent space dimentions is given as 24, which corresponds to 2 dimensions in 12 viewing directions Exp. 1 : DISENTANGLING 2D IMAGE ROTATION Reconstructions of the test dataset. An input and reconstructions in given rotation angles generated by are presented from the left column of each row.
  • 10. EXPERIMENTAL RESULTS Exp. 2 : DISENTANGLING 3D OBJECT ROTATION • 809 chair models are selected • The first 500 models are used as a training set and the remaining 309 models are used as a test set. • Each chair model is rendered from 31 azimuth angles and 2 elevation angles (20 and 30) • A deep convolutional encoder-decoder architecture are used. • The number of the latent space dimensions is given as 992, which corresponds to 32 dimensions in 31 viewing directions.
  • 11. EXPERIMENTAL RESULTS Exp. 2 : DISENTANGLING 3D OBJECT ROTATION (a): A network architecture used in the experiment of 3D object rotation. (b): Reconstructions of the test dataset. An input and reconstructions in given rotation angles are shown from the left column of each row.