SlideShare a Scribd company logo
1 of 25
Download to read offline
2020/09/08
Ho Seong Lee (hoya012)
Cognex Deep Learning Lab
Research Engineer
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 1
Contents
• Introduction
• Related Work
• New Benchmarks
• DeepAugment
• Experiments
• Conclusion
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 2
Introduction
Human vision system is robust, but existing vision models are not robust.
• Humans can deal with many forms of corruption such as blur, pixel noise and abstract change in
structure and style.
• Achieving robustness is essential in safety-critical and accuracy-critical applications.
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 3
Dog! Dog!Dog! Dog!
Dog! starfish! baseball! drumstick!
Introduction
Most work on robustness methods for vision has focused on adversarial examples.
• For standardizing and expanding the robustness topic, several studies have begun.
• At first, establish benchmark dataset and evaluation metric.
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 4
Related Works
Pioneers of robustness in ML - Dan Hendrycks (My Favorite Researcher..)
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 5
Reference: https://people.eecs.berkeley.edu/~hendrycks/
Related Works
Pioneers of robustness in ML – Madry Lab
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 6
Reference: http://madry-lab.ml/
Related Works
Pioneers of robustness in ML – Bethge Lab
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 7
Reference: http://bethgelab.org/
Related Works
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 8
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
• Create ImageNet-C and ImageNet-P test set and Benchmarks.
ImageNet-C ImageNet-P
Related Works
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 9
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
• Robustness Metrics
= 𝑎𝑣𝑒𝑟𝑎𝑔𝑒 ( )
* each level of severity s (1 ≤ s ≤ 5).
ImageNet-C
ImageNet-P
Related Works
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 10
Natural Adversarial Examples
• Introduce natural adversarial examples and create 7,500 ImageNet-A test set. (200 class)
• Download numerous images related to an ImageNet class from website iNaturalist and Flickr.
• Delete the images that ResNet-50 correctly classify. Finally, select a subset of high-quality images.
ImageNet-A
Related Works
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 11
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
• Propose a technique to improve the robustness and uncertainty estimates of image classifiers.
• Use JS Divergence Consistency loss
New Benchmarks
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 12
Seven robustness hypotheses
• Larger Models: increasing model size improves robustness.
• Self-Attention: adding self-attention layers to models improves robustness.
• Diverse Data Augmentation: robustness can increase through data augmentation.
• Pretraining: pretraining on larger and more diverse datasets improves robustness.
• Texture Bias: convolutional networks are biased towards texture, which harms robustness.
• Only IID Accuracy Matters: accuracy on independent and identically distributed test data entirely
determines natural robustness.
• Synthetic ≠Natural: synthetic robustness interventions including diverse data augmentations do not help
with robustness on naturally occurring distribution shifts.
New Benchmarks
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 13
Introduce three new robustness benchmarks
• It has been difficult to arbitrate these hypotheses because existing robustness datasets preclude the
possibility of controlled experiments by varying multiple aspects simultaneously.
• To address these issues and test the seven hypotheses outlined above, create new test sets.
New Benchmarks
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 14
ImageNet-Renditions (ImageNet-R)
• 30,000 test set containing various renditions (e.g., paintings, embroidery, etc.) of ImageNet object
classes (200). The rendition styles (“Painting”, “Toy”) are not ImageNet-R’s classes.
• Original ImageNet dataset discouraged such images since annotators were instructed to collect “photos
only, no painting, no drawings, etc.” (Deng, 2012). Authors do the opposite.
New Benchmarks
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 15
StreetView StoreFronts (SVSF)
• Contains business storefront images taken from Google Streetview (20 classes).
• Investigate natural shifts in the image capture process using metadata (e.g. location, year, camera type)
• Create one training set(200K) and five in-distribution test set(10K) from images taken in
US/Mexico/Canada during 2019 using “new” camera. Unfortunately, unleased..
• Make four out-of-distribution test set(10K): “2017”, “2018”, “France”, “old camera”
New Benchmarks
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 16
DeepFashion Remixed
• Changes in camera operation can cause shifts in attributes such as object size, object occlusion, camera
viewpoint, and camera zoom.
• To measure this, create multi-labeled training set(48K) and 8 out-of-distribution test set (Total 121K).
Medium scale, Medium occlusion,
side/back viewpoint, no zoom-in
Small and large scale,
Minimal and heavy occlusion,
Frontal and not-worn viewpoints,
Medium and large zoom-in
DeepAugment
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 17
New data augmentation technique: DeepAugment
• In order to explore the Diverse Data Augmentation hypothesis, introduce a new data augmentation.
• Pass an image through an img-to-img networks (such as autoencoder or SR network)
• But rather than processing the image normally, distort the internal weights and activations by applying
randomly sampled ops(zeroing, negating, convolving, transposing), applying activation functions on.
• This creates diverse but semantically consistent images.
DeepAugment
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 18
Experiments
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 19
Experimental Setup
Experiments
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 20
Experimental Results: ImageNet-R
• ImageNet-200: The original ImageNet test set restricted to ImageNet-R’s 200 classes.
• Pretraining → improves IID/OOD gap with very small portion.
• Self-Attention → increase IID/OOD gap
• Diverse Data Augmentation, Larger Models → improves IID/OOD gap significantly!
OODIID
Diff
-0.2
0.0
0.2
-12.5
-2.0
-6.4
-7.1
-5.7
-10.8
-4.1
Error Rate (↓)
Experiments
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 21
Experimental Results: StreetView StoreFronts
• No method helps much on country shift, where error rates roughly double across the board.
• Images captured in France contain noticeably different architecture styles and storefront designs.
• Unable to find conspicuous and consistent indicators of the camera and year. → insensitive feature.
• Data augmentation primarily helps combat texture bias as with ImageNet-R.
• But existing augmentations are not diverse enough to capture high-level semantic shifts such as building
architecture. Error Rate (↓)
Experiments
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 22
Experimental Results: DeepFashion Remixed
• All evaluated methods have an average OOD mAP that is close to the baseline.
• DFR’s size and occlusion shifts hurt performance the most.
• Nothing substantially improved OOD performance beyond what is explained by IID performance, so here
it would appear that Only IID Accuracy Matters.
mAP scores (↑)
Experiments
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 23
Experimental Results: ImageNet-C
• DeepAugment + AugMix → attain the SOTA result.
• Evidence for Larger Models, Self-Attention, Diverse Data Augmentation, Pretraining, and Texture Bias.
• Evidence against the Only IID Accuracy Matters.
Error Rate, mCE (↓)
Experiments
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 24
Experimental Results: Real Blurry Images
• ImageNet-C use various synthetic corruptions that have different from real-world.
• Collect a small dataset of 1,000 real-world blurry images and evaluate various models.
• Everything that helped in ImageNet-C was also helpful in Real Blurry Images.
• Evidence against the Synthetic ≠Natural.
Error Rate (↓)
Conclusion
SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
• Introduce three new benchmarks, ImageNet-R, SVSF, and DFR. (+ Real Blurry Images)
• Introduce new data augmentation technique DeepAugment.
• With these benchmarks, evaluate seven robustness hypotheses.
• It seems that robustness has a many faces (multivariate).
• If so, research community should prioritize creating new robustness methods.
25

More Related Content

What's hot

A systematic study of the class imbalance problem in convolutional neural net...
A systematic study of the class imbalance problem in convolutional neural net...A systematic study of the class imbalance problem in convolutional neural net...
A systematic study of the class imbalance problem in convolutional neural net...Yuya Soneoka
 
RecSysOps: Best Practices for Operating a Large-Scale Recommender System
RecSysOps: Best Practices for Operating a Large-Scale Recommender SystemRecSysOps: Best Practices for Operating a Large-Scale Recommender System
RecSysOps: Best Practices for Operating a Large-Scale Recommender SystemEhsan38
 
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion ModelsDeep Learning JP
 
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...Deep Learning JP
 
[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image Synthesis
[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image Synthesis[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image Synthesis
[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image SynthesisDeep Learning JP
 
[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People Images
[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People Images[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People Images
[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People ImagesDeep Learning JP
 
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...Sunghoon Joo
 
Unsupervised visual representation learning overview: Toward Self-Supervision
Unsupervised visual representation learning overview: Toward Self-SupervisionUnsupervised visual representation learning overview: Toward Self-Supervision
Unsupervised visual representation learning overview: Toward Self-SupervisionLEE HOSEONG
 
Generating Diverse High-Fidelity Images with VQ-VAE-2
Generating Diverse High-Fidelity Images with VQ-VAE-2Generating Diverse High-Fidelity Images with VQ-VAE-2
Generating Diverse High-Fidelity Images with VQ-VAE-2harmonylab
 
【論文読み会】Universal Language Model Fine-tuning for Text Classification
【論文読み会】Universal Language Model Fine-tuning for Text Classification【論文読み会】Universal Language Model Fine-tuning for Text Classification
【論文読み会】Universal Language Model Fine-tuning for Text ClassificationARISE analytics
 
Kdd 2014 Tutorial - the recommender problem revisited
Kdd 2014 Tutorial -  the recommender problem revisitedKdd 2014 Tutorial -  the recommender problem revisited
Kdd 2014 Tutorial - the recommender problem revisitedXavier Amatriain
 
CONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORKCONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORKMd Rajib Bhuiyan
 
文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted WindowsToru Tamaki
 
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...Sunghoon Joo
 
ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksKouhei Nakajima
 
AI勉強会用スライド
AI勉強会用スライドAI勉強会用スライド
AI勉強会用スライドharmonylab
 
CycleGAN이 무엇인지 알아보자
CycleGAN이 무엇인지 알아보자CycleGAN이 무엇인지 알아보자
CycleGAN이 무엇인지 알아보자Kwangsik Lee
 
G社のNMT論文を読んでみた
G社のNMT論文を読んでみたG社のNMT論文を読んでみた
G社のNMT論文を読んでみたToshiaki Nakazawa
 
제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스
제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스
제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스BOAZ Bigdata
 
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionPR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionSungchul Kim
 

What's hot (20)

A systematic study of the class imbalance problem in convolutional neural net...
A systematic study of the class imbalance problem in convolutional neural net...A systematic study of the class imbalance problem in convolutional neural net...
A systematic study of the class imbalance problem in convolutional neural net...
 
RecSysOps: Best Practices for Operating a Large-Scale Recommender System
RecSysOps: Best Practices for Operating a Large-Scale Recommender SystemRecSysOps: Best Practices for Operating a Large-Scale Recommender System
RecSysOps: Best Practices for Operating a Large-Scale Recommender System
 
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
 
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
【DL輪読会】Poisoning Language Models During Instruction Tuning Instruction Tuning...
 
[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image Synthesis
[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image Synthesis[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image Synthesis
[DL輪読会]Large Scale GAN Training for High Fidelity Natural Image Synthesis
 
[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People Images
[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People Images[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People Images
[DL輪読会] The Conditional Analogy GAN: Swapping Fashion Articles on People Images
 
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
 
Unsupervised visual representation learning overview: Toward Self-Supervision
Unsupervised visual representation learning overview: Toward Self-SupervisionUnsupervised visual representation learning overview: Toward Self-Supervision
Unsupervised visual representation learning overview: Toward Self-Supervision
 
Generating Diverse High-Fidelity Images with VQ-VAE-2
Generating Diverse High-Fidelity Images with VQ-VAE-2Generating Diverse High-Fidelity Images with VQ-VAE-2
Generating Diverse High-Fidelity Images with VQ-VAE-2
 
【論文読み会】Universal Language Model Fine-tuning for Text Classification
【論文読み会】Universal Language Model Fine-tuning for Text Classification【論文読み会】Universal Language Model Fine-tuning for Text Classification
【論文読み会】Universal Language Model Fine-tuning for Text Classification
 
Kdd 2014 Tutorial - the recommender problem revisited
Kdd 2014 Tutorial -  the recommender problem revisitedKdd 2014 Tutorial -  the recommender problem revisited
Kdd 2014 Tutorial - the recommender problem revisited
 
CONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORKCONVOLUTIONAL NEURAL NETWORK
CONVOLUTIONAL NEURAL NETWORK
 
文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
文献紹介:Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows
 
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
 
ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks
 
AI勉強会用スライド
AI勉強会用スライドAI勉強会用スライド
AI勉強会用スライド
 
CycleGAN이 무엇인지 알아보자
CycleGAN이 무엇인지 알아보자CycleGAN이 무엇인지 알아보자
CycleGAN이 무엇인지 알아보자
 
G社のNMT論文を読んでみた
G社のNMT論文を読んでみたG社のNMT論文を読んでみた
G社のNMT論文を読んでみた
 
제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스
제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스
제 16회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [기린그림 팀] : 사용자의 손글씨가 담긴 그림 일기 생성 서비스
 
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionPR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
 

Similar to "The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization" Paper Review

How useful is self-supervised pretraining for Visual tasks?
How useful is self-supervised pretraining for Visual tasks?How useful is self-supervised pretraining for Visual tasks?
How useful is self-supervised pretraining for Visual tasks?Seunghyun Hwang
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonAditya Bhattacharya
 
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019Universitat Politècnica de Catalunya
 
深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用CHENHuiMei
 
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Universitat Politècnica de Catalunya
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용홍배 김
 
A Re-evaluation of Pedestrian Detection on Riemannian Manifolds
A Re-evaluation of Pedestrian Detection on Riemannian ManifoldsA Re-evaluation of Pedestrian Detection on Riemannian Manifolds
A Re-evaluation of Pedestrian Detection on Riemannian ManifoldsDiego Tosato
 
Exploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation LearningExploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation LearningSangmin Woo
 
A Fully Progressive approach to Single image super-resolution
A Fully Progressive approach to Single image super-resolution A Fully Progressive approach to Single image super-resolution
A Fully Progressive approach to Single image super-resolution Mohammed Ashour
 
Dependency Injection in .NET applications
Dependency Injection in .NET applicationsDependency Injection in .NET applications
Dependency Injection in .NET applicationsBabak Naffas
 
IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...
IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...
IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...IRJET Journal
 
Chapter 6- Classification and Prediction Methods
Chapter 6- Classification and Prediction MethodsChapter 6- Classification and Prediction Methods
Chapter 6- Classification and Prediction MethodsBenjJamiesonDuag2
 
Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019Aditya Bhattacharya
 
do adversarially robust image net models transfer better
do adversarially robust image net models transfer betterdo adversarially robust image net models transfer better
do adversarially robust image net models transfer betterLEE HOSEONG
 
Architecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IArchitecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IWanjin Yu
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slideswolf
 
Graph Community Detection Algorithm for Distributed Memory Parallel Computing...
Graph Community Detection Algorithm for Distributed Memory Parallel Computing...Graph Community Detection Algorithm for Distributed Memory Parallel Computing...
Graph Community Detection Algorithm for Distributed Memory Parallel Computing...Alexander Pozdneev
 

Similar to "The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization" Paper Review (20)

How useful is self-supervised pretraining for Visual tasks?
How useful is self-supervised pretraining for Visual tasks?How useful is self-supervised pretraining for Visual tasks?
How useful is self-supervised pretraining for Visual tasks?
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
Neural Architectures for Still Images - Xavier Giro- UPC Barcelona 2019
 
Fa19_P1.pptx
Fa19_P1.pptxFa19_P1.pptx
Fa19_P1.pptx
 
深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用
 
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
 
A Re-evaluation of Pedestrian Detection on Riemannian Manifolds
A Re-evaluation of Pedestrian Detection on Riemannian ManifoldsA Re-evaluation of Pedestrian Detection on Riemannian Manifolds
A Re-evaluation of Pedestrian Detection on Riemannian Manifolds
 
Exploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation LearningExploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation Learning
 
A Fully Progressive approach to Single image super-resolution
A Fully Progressive approach to Single image super-resolution A Fully Progressive approach to Single image super-resolution
A Fully Progressive approach to Single image super-resolution
 
AlexNet
AlexNetAlexNet
AlexNet
 
Dependency Injection in .NET applications
Dependency Injection in .NET applicationsDependency Injection in .NET applications
Dependency Injection in .NET applications
 
IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...
IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...
IRJET - Multi-Label Road Scene Prediction for Autonomous Vehicles using Deep ...
 
Chapter 6- Classification and Prediction Methods
Chapter 6- Classification and Prediction MethodsChapter 6- Classification and Prediction Methods
Chapter 6- Classification and Prediction Methods
 
Person Recognition
Person RecognitionPerson Recognition
Person Recognition
 
Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019
 
do adversarially robust image net models transfer better
do adversarially robust image net models transfer betterdo adversarially robust image net models transfer better
do adversarially robust image net models transfer better
 
Architecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IArchitecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks I
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slides
 
Graph Community Detection Algorithm for Distributed Memory Parallel Computing...
Graph Community Detection Algorithm for Distributed Memory Parallel Computing...Graph Community Detection Algorithm for Distributed Memory Parallel Computing...
Graph Community Detection Algorithm for Distributed Memory Parallel Computing...
 

More from LEE HOSEONG

Unsupervised anomaly detection using style distillation
Unsupervised anomaly detection using style distillationUnsupervised anomaly detection using style distillation
Unsupervised anomaly detection using style distillationLEE HOSEONG
 
CNN Architecture A to Z
CNN Architecture A to ZCNN Architecture A to Z
CNN Architecture A to ZLEE HOSEONG
 
carrier of_tricks_for_image_classification
carrier of_tricks_for_image_classificationcarrier of_tricks_for_image_classification
carrier of_tricks_for_image_classificationLEE HOSEONG
 
Mixed Precision Training Review
Mixed Precision Training ReviewMixed Precision Training Review
Mixed Precision Training ReviewLEE HOSEONG
 
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionMVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionLEE HOSEONG
 
YOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewYOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewLEE HOSEONG
 
FixMatch:simplifying semi supervised learning with consistency and confidence
FixMatch:simplifying semi supervised learning with consistency and confidenceFixMatch:simplifying semi supervised learning with consistency and confidence
FixMatch:simplifying semi supervised learning with consistency and confidenceLEE HOSEONG
 
"Revisiting self supervised visual representation learning" Paper Review
"Revisiting self supervised visual representation learning" Paper Review"Revisiting self supervised visual representation learning" Paper Review
"Revisiting self supervised visual representation learning" Paper ReviewLEE HOSEONG
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewLEE HOSEONG
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution OverviewLEE HOSEONG
 
2019 ICLR Best Paper Review
2019 ICLR Best Paper Review2019 ICLR Best Paper Review
2019 ICLR Best Paper ReviewLEE HOSEONG
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overviewLEE HOSEONG
 
"Google Vizier: A Service for Black-Box Optimization" Paper Review
"Google Vizier: A Service for Black-Box Optimization" Paper Review"Google Vizier: A Service for Black-Box Optimization" Paper Review
"Google Vizier: A Service for Black-Box Optimization" Paper ReviewLEE HOSEONG
 
"Searching for Activation Functions" Paper Review
"Searching for Activation Functions" Paper Review"Searching for Activation Functions" Paper Review
"Searching for Activation Functions" Paper ReviewLEE HOSEONG
 
"Learning transferable architectures for scalable image recognition" Paper Re...
"Learning transferable architectures for scalable image recognition" Paper Re..."Learning transferable architectures for scalable image recognition" Paper Re...
"Learning transferable architectures for scalable image recognition" Paper Re...LEE HOSEONG
 
"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper Review
"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper Review"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper Review
"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper ReviewLEE HOSEONG
 
"Dataset and metrics for predicting local visible differences" Paper Review
"Dataset and metrics for predicting local visible differences" Paper Review"Dataset and metrics for predicting local visible differences" Paper Review
"Dataset and metrics for predicting local visible differences" Paper ReviewLEE HOSEONG
 
"From image level to pixel-level labeling with convolutional networks" Paper ...
"From image level to pixel-level labeling with convolutional networks" Paper ..."From image level to pixel-level labeling with convolutional networks" Paper ...
"From image level to pixel-level labeling with convolutional networks" Paper ...LEE HOSEONG
 
"simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r..."simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r...LEE HOSEONG
 
"How does batch normalization help optimization" Paper Review
"How does batch normalization help optimization" Paper Review"How does batch normalization help optimization" Paper Review
"How does batch normalization help optimization" Paper ReviewLEE HOSEONG
 

More from LEE HOSEONG (20)

Unsupervised anomaly detection using style distillation
Unsupervised anomaly detection using style distillationUnsupervised anomaly detection using style distillation
Unsupervised anomaly detection using style distillation
 
CNN Architecture A to Z
CNN Architecture A to ZCNN Architecture A to Z
CNN Architecture A to Z
 
carrier of_tricks_for_image_classification
carrier of_tricks_for_image_classificationcarrier of_tricks_for_image_classification
carrier of_tricks_for_image_classification
 
Mixed Precision Training Review
Mixed Precision Training ReviewMixed Precision Training Review
Mixed Precision Training Review
 
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionMVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
 
YOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewYOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection review
 
FixMatch:simplifying semi supervised learning with consistency and confidence
FixMatch:simplifying semi supervised learning with consistency and confidenceFixMatch:simplifying semi supervised learning with consistency and confidence
FixMatch:simplifying semi supervised learning with consistency and confidence
 
"Revisiting self supervised visual representation learning" Paper Review
"Revisiting self supervised visual representation learning" Paper Review"Revisiting self supervised visual representation learning" Paper Review
"Revisiting self supervised visual representation learning" Paper Review
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 Review
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution Overview
 
2019 ICLR Best Paper Review
2019 ICLR Best Paper Review2019 ICLR Best Paper Review
2019 ICLR Best Paper Review
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overview
 
"Google Vizier: A Service for Black-Box Optimization" Paper Review
"Google Vizier: A Service for Black-Box Optimization" Paper Review"Google Vizier: A Service for Black-Box Optimization" Paper Review
"Google Vizier: A Service for Black-Box Optimization" Paper Review
 
"Searching for Activation Functions" Paper Review
"Searching for Activation Functions" Paper Review"Searching for Activation Functions" Paper Review
"Searching for Activation Functions" Paper Review
 
"Learning transferable architectures for scalable image recognition" Paper Re...
"Learning transferable architectures for scalable image recognition" Paper Re..."Learning transferable architectures for scalable image recognition" Paper Re...
"Learning transferable architectures for scalable image recognition" Paper Re...
 
"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper Review
"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper Review"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper Review
"Learning From Noisy Large-Scale Datasets With Minimal Supervision" Paper Review
 
"Dataset and metrics for predicting local visible differences" Paper Review
"Dataset and metrics for predicting local visible differences" Paper Review"Dataset and metrics for predicting local visible differences" Paper Review
"Dataset and metrics for predicting local visible differences" Paper Review
 
"From image level to pixel-level labeling with convolutional networks" Paper ...
"From image level to pixel-level labeling with convolutional networks" Paper ..."From image level to pixel-level labeling with convolutional networks" Paper ...
"From image level to pixel-level labeling with convolutional networks" Paper ...
 
"simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r..."simple does it weakly supervised instance and semantic segmentation" Paper r...
"simple does it weakly supervised instance and semantic segmentation" Paper r...
 
"How does batch normalization help optimization" Paper Review
"How does batch normalization help optimization" Paper Review"How does batch normalization help optimization" Paper Review
"How does batch normalization help optimization" Paper Review
 

Recently uploaded

New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsPrecisely
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 

Recently uploaded (20)

New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power Systems
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 

"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization" Paper Review

  • 1. 2020/09/08 Ho Seong Lee (hoya012) Cognex Deep Learning Lab Research Engineer SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 1
  • 2. Contents • Introduction • Related Work • New Benchmarks • DeepAugment • Experiments • Conclusion SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 2
  • 3. Introduction Human vision system is robust, but existing vision models are not robust. • Humans can deal with many forms of corruption such as blur, pixel noise and abstract change in structure and style. • Achieving robustness is essential in safety-critical and accuracy-critical applications. SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 3 Dog! Dog!Dog! Dog! Dog! starfish! baseball! drumstick!
  • 4. Introduction Most work on robustness methods for vision has focused on adversarial examples. • For standardizing and expanding the robustness topic, several studies have begun. • At first, establish benchmark dataset and evaluation metric. SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 4
  • 5. Related Works Pioneers of robustness in ML - Dan Hendrycks (My Favorite Researcher..) SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 5 Reference: https://people.eecs.berkeley.edu/~hendrycks/
  • 6. Related Works Pioneers of robustness in ML – Madry Lab SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 6 Reference: http://madry-lab.ml/
  • 7. Related Works Pioneers of robustness in ML – Bethge Lab SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 7 Reference: http://bethgelab.org/
  • 8. Related Works SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 8 Benchmarking Neural Network Robustness to Common Corruptions and Perturbations • Create ImageNet-C and ImageNet-P test set and Benchmarks. ImageNet-C ImageNet-P
  • 9. Related Works SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 9 Benchmarking Neural Network Robustness to Common Corruptions and Perturbations • Robustness Metrics = 𝑎𝑣𝑒𝑟𝑎𝑔𝑒 ( ) * each level of severity s (1 ≤ s ≤ 5). ImageNet-C ImageNet-P
  • 10. Related Works SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 10 Natural Adversarial Examples • Introduce natural adversarial examples and create 7,500 ImageNet-A test set. (200 class) • Download numerous images related to an ImageNet class from website iNaturalist and Flickr. • Delete the images that ResNet-50 correctly classify. Finally, select a subset of high-quality images. ImageNet-A
  • 11. Related Works SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 11 AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty • Propose a technique to improve the robustness and uncertainty estimates of image classifiers. • Use JS Divergence Consistency loss
  • 12. New Benchmarks SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 12 Seven robustness hypotheses • Larger Models: increasing model size improves robustness. • Self-Attention: adding self-attention layers to models improves robustness. • Diverse Data Augmentation: robustness can increase through data augmentation. • Pretraining: pretraining on larger and more diverse datasets improves robustness. • Texture Bias: convolutional networks are biased towards texture, which harms robustness. • Only IID Accuracy Matters: accuracy on independent and identically distributed test data entirely determines natural robustness. • Synthetic ≠Natural: synthetic robustness interventions including diverse data augmentations do not help with robustness on naturally occurring distribution shifts.
  • 13. New Benchmarks SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 13 Introduce three new robustness benchmarks • It has been difficult to arbitrate these hypotheses because existing robustness datasets preclude the possibility of controlled experiments by varying multiple aspects simultaneously. • To address these issues and test the seven hypotheses outlined above, create new test sets.
  • 14. New Benchmarks SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 14 ImageNet-Renditions (ImageNet-R) • 30,000 test set containing various renditions (e.g., paintings, embroidery, etc.) of ImageNet object classes (200). The rendition styles (“Painting”, “Toy”) are not ImageNet-R’s classes. • Original ImageNet dataset discouraged such images since annotators were instructed to collect “photos only, no painting, no drawings, etc.” (Deng, 2012). Authors do the opposite.
  • 15. New Benchmarks SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 15 StreetView StoreFronts (SVSF) • Contains business storefront images taken from Google Streetview (20 classes). • Investigate natural shifts in the image capture process using metadata (e.g. location, year, camera type) • Create one training set(200K) and five in-distribution test set(10K) from images taken in US/Mexico/Canada during 2019 using “new” camera. Unfortunately, unleased.. • Make four out-of-distribution test set(10K): “2017”, “2018”, “France”, “old camera”
  • 16. New Benchmarks SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 16 DeepFashion Remixed • Changes in camera operation can cause shifts in attributes such as object size, object occlusion, camera viewpoint, and camera zoom. • To measure this, create multi-labeled training set(48K) and 8 out-of-distribution test set (Total 121K). Medium scale, Medium occlusion, side/back viewpoint, no zoom-in Small and large scale, Minimal and heavy occlusion, Frontal and not-worn viewpoints, Medium and large zoom-in
  • 17. DeepAugment SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 17 New data augmentation technique: DeepAugment • In order to explore the Diverse Data Augmentation hypothesis, introduce a new data augmentation. • Pass an image through an img-to-img networks (such as autoencoder or SR network) • But rather than processing the image normally, distort the internal weights and activations by applying randomly sampled ops(zeroing, negating, convolving, transposing), applying activation functions on. • This creates diverse but semantically consistent images.
  • 18. DeepAugment SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 18
  • 19. Experiments SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 19 Experimental Setup
  • 20. Experiments SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 20 Experimental Results: ImageNet-R • ImageNet-200: The original ImageNet test set restricted to ImageNet-R’s 200 classes. • Pretraining → improves IID/OOD gap with very small portion. • Self-Attention → increase IID/OOD gap • Diverse Data Augmentation, Larger Models → improves IID/OOD gap significantly! OODIID Diff -0.2 0.0 0.2 -12.5 -2.0 -6.4 -7.1 -5.7 -10.8 -4.1 Error Rate (↓)
  • 21. Experiments SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 21 Experimental Results: StreetView StoreFronts • No method helps much on country shift, where error rates roughly double across the board. • Images captured in France contain noticeably different architecture styles and storefront designs. • Unable to find conspicuous and consistent indicators of the camera and year. → insensitive feature. • Data augmentation primarily helps combat texture bias as with ImageNet-R. • But existing augmentations are not diverse enough to capture high-level semantic shifts such as building architecture. Error Rate (↓)
  • 22. Experiments SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 22 Experimental Results: DeepFashion Remixed • All evaluated methods have an average OOD mAP that is close to the baseline. • DFR’s size and occlusion shifts hurt performance the most. • Nothing substantially improved OOD performance beyond what is explained by IID performance, so here it would appear that Only IID Accuracy Matters. mAP scores (↑)
  • 23. Experiments SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 23 Experimental Results: ImageNet-C • DeepAugment + AugMix → attain the SOTA result. • Evidence for Larger Models, Self-Attention, Diverse Data Augmentation, Pretraining, and Texture Bias. • Evidence against the Only IID Accuracy Matters. Error Rate, mCE (↓)
  • 24. Experiments SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization 24 Experimental Results: Real Blurry Images • ImageNet-C use various synthetic corruptions that have different from real-world. • Collect a small dataset of 1,000 real-world blurry images and evaluate various models. • Everything that helped in ImageNet-C was also helpful in Real Blurry Images. • Evidence against the Synthetic ≠Natural. Error Rate (↓)
  • 25. Conclusion SNUAI 8th | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization • Introduce three new benchmarks, ImageNet-R, SVSF, and DFR. (+ Real Blurry Images) • Introduce new data augmentation technique DeepAugment. • With these benchmarks, evaluate seven robustness hypotheses. • It seems that robustness has a many faces (multivariate). • If so, research community should prioritize creating new robustness methods. 25