A simple way to make neural networks robust against diverse image corruptions

Evgenia Rusak, Lukas Schott, R. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge, Wieland Brendel

Type: Preprint

Publication Date: 2020-01-16

Citations: 31

View

Locations

arXiv (Cornell University) - View

Similar Works

Action	Title	Year	Authors
+	A simple way to make neural networks robust against diverse image corruptions	2020	Evgenia Rusak Lukas Schott R. Zimmermann Julian Bitterwolf Oliver Bringmann Matthias Bethge Wieland Brendel
+	Increasing the robustness of DNNs against image corruptions by playing the Game of Noise	2020	Evgenia Rusak Lukas Schott R. Zimmermann Julian Bitterwolf Oliver Bringmann Matthias Bethge Wieland Brendel
+	Defending Against Image Corruptions Through Adversarial Augmentations	2021	Dan A. Calian Florian Stimberg Olivia Wiles Sylvestre-Alvise Rebuffi András György Timothy Mann Sven Gowal
+	Defending Against Image Corruptions Through Adversarial Augmentations	2021	Dan A. Calian Florian Stimberg Olivia Wiles Sylvestre-Alvise Rebuffi András György Timothy Mann Sven Gowal
+ PDF Chat	A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions	2020	Evgenia Rusak Lukas Schott R. Zimmermann Julian Bitterwolf Oliver Bringmann Matthias Bethge Wieland Brendel
+	Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations	2018	Dan Hendrycks Thomas G. Dietterich
+	Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense	2023	Zunzhi You Daochang Liu Chang Xu
+	PRIME: A few primitives can boost robustness to common corruptions	2021	Apostolos Modas Rahul Rade Guillermo Ortiz-Jiménez Seyed-Mohsen Moosavi-Dezfooli Pascal Frossard
+	MNIST-C: A Robustness Benchmark for Computer Vision	2019	Norman Mu Justin Gilmer
+	Improving robustness against common corruptions by covariate shift adaptation	2020	Steffen Schneider Evgenia Rusak Luisa Eck Oliver Bringmann Wieland Brendel Matthias Bethge
+	Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions	2023	Harshitha Machiraju Michael H. Herzog Pascal Frossard
+ PDF Chat	Improving robustness against common corruptions with frequency biased models	2021	Tonmoy Saikia Cordelia Schmid Thomas Brox
+	On the effectiveness of adversarial training against common corruptions	2021	Klim Kireev Maksym Andriushchenko Nicolas Flammarion
+	On the effectiveness of adversarial training against common corruptions.	2021	Klim Kireev Maksym Andriushchenko Nicolas Flammarion
+	Improving robustness against common corruptions with frequency biased models	2021	Tonmoy Saikia Cordelia Schmid Thomas Brox
+	Improving robustness against common corruptions with frequency biased models	2021	Tonmoy Saikia Cordelia Schmid Thomas Brox
+ PDF Chat	Improving robustness to corruptions with multiplicative weight perturbations	2024	Trung Trinh Markus Heinonen Luigi Acerbi Samuel Kaski
+ PDF Chat	Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration	2023	Theodoros Tsiligkaridis Athanasios Tsiligkaridis
+ PDF Chat	Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond	2022	Yi Yu Wenhan Yang Yap‐Peng Tan Alex C. Kot
+	Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond	2022	Yi Yu Wenhan Yang Yap‐Peng Tan Alex C. Kot

Cited by (28)

Action	Title	Year	Authors
+ PDF Chat	Multimodal Co-learning: Challenges, applications with datasets, recent advances and future directions	2021	Anil Rahate Rahee Walambe Sheela Ramanna Ketan Kotecha
+	Learning perturbation sets for robust machine learning	2020	Eric Wong J. Zico Kolter
+	Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization	2021	Manli Shu Zuxuan Wu Micah Goldblum Tom Goldstein
+	Untapped Potential of Data Augmentation: A Domain Generalization Viewpoint	2020	Vihari Piratla Shiv Shankar
+	Improved Handling of Motion Blur in Online Object Detection	2020	Mohamed Sayed Gabriel Brostow
+	A Closer Look at the Robustness of Vision-and-Language Pre-trained Models	2020	Linjie Li Zhe Gan Jingjing Liu
+ PDF Chat	The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization	2021	Dan Hendrycks Steven Basart Norman Mu Saurav Kadavath Fengqiu Wang Evan Dorundo Rahul Desai Tyler Zhu Samyak Parajuli Mike Guo
+ PDF Chat	Adversarial momentum-contrastive pre-training	2022	Cong Xu Dan Li Min Yang
+	Bio-inspired Robustness: A Review	2021	Harshitha Machiraju Oh-Hyeon Choung Pascal Frossard Michael H. Herzog
+ PDF Chat	Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries	2021	Kun-Peng Ning Lue Tao Songcan Chen Sheng-Jun Huang
+	Utilizing a null class to restrict decision spaces and defend against neural network adversarial attacks	2020	Matthew J. Roos
+	Using Learning Dynamics to Explore the Role of Implicit Regularization in Adversarial Examples	2020	Josue Ortega Yilong Ju Ryan Pyle Ankit Patel
+ PDF Chat	CrossNorm and SelfNorm for Generalization under Distribution Shifts	2021	Zhiqiang Tang Yunhe Gao Yi Zhu Zhi Zhang Mu Li Dimitris Metaxas
+	Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation	2021	Chaithanya Kumar Mummadi Robin Hutmacher Kilian Rambach Evgeny Levinkov Thomas Brox Jan Hendrik Metzen
+	Impact of Aliasing on Generalization in Deep Convolutional Networks	2021	Cristina Nader Vasconcelos Hugo Larochelle Vincent Dumoulin Rob Romijnders Nicolas Le Roux Ross Goroshin
+	SelfNorm and CrossNorm for Out-of-Distribution Robustness	2021	Zhiqiang Tang Yunhe Gao Yi Zhu Zhi Zhang Mu Li Dimitris Metaxas
+	Rethinking the Design Principles of Robust Vision Transformer	2021	Xiaofeng Mao Gege Qi Yuefeng Chen Xiaodan Li Shaokai Ye Yuan He Hui Xue
+	An Effective Anti-Aliasing Approach for Residual Networks	2020	Cristina Nader Vasconcelos Hugo Larochelle Vincent Dumoulin Nicolas Le Roux Ross Goroshin
+	Defending Against Image Corruptions Through Adversarial Augmentations	2021	Dan A. Calian Florian Stimberg Olivia Wiles Sylvestre-Alvise Rebuffi András György Timothy Mann Sven Gowal
+	Theoretical Study of Random Noise Defense against Query-Based Black-Box Attacks.	2021	Zeyu Qin Yanbo Fan Hongyuan Zha Baoyuan Wu
+	Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs	2021	Avinash Baidya Joel Dapello James J. DiCarlo Tiago Marques
+	Nuisance-Label Supervision: Robustness Improvement by Free Labels	2021	Xinyue Wei Weichao Qiu Yi Zhang Zihao Xiao Alan Yuille
+ PDF Chat	Robust Image Classification Using a Low-Pass Activation Function and DCT Augmentation	2021	Md. Tahmid Hossain Shyh Wei Teng Ferdous Sohel Guojun Lu
+	On the effectiveness of adversarial training against common corruptions.	2021	Klim Kireev Maksym Andriushchenko Nicolas Flammarion
+	Multispectral Object Detection with Deep Learning	2021	Osman Gani Somenath Kuiry Alaka Das Mita Nasipuri Nibaran Das
+ PDF Chat	Deepfake Forensics via an Adversarial Game	2022	Wang Zhi Yiwen Guo Wangmeng Zuo
+ PDF Chat	On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness	2021	Eric Mintun Alexander Kirillov Saining Xie
+	Improving robustness against common corruptions with frequency biased models	2021	Tonmoy Saikia Cordelia Schmid Thomas Brox

Citing (31)

Action	Title	Year	Authors
+ PDF Chat	ImageNet Large Scale Visual Recognition Challenge	2015	Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael S. Bernstein
+ PDF Chat	Deep Residual Learning for Image Recognition	2016	Kaiming He Xiangyu Zhang Shaoqing Ren Jian Sun
+	Achieving Human Parity in Conversational Speech Recognition	2016	Wayne Xiong Jasha Droppo Xuedong Huang Frank Seide Mike Seltzer Andreas Stolcke Dong Yu Geoffrey Zweig
+ PDF Chat	Universal Adversarial Perturbations	2017	Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi Omar Fawzi Pascal Frossard
+	Quality Resilient Deep Neural Networks	2017	Samuel Dodge Lina J. Karam
+ PDF Chat	A Study and Comparison of Human and Deep Learning Recognition Performance under Visual Distortions	2017	Samuel Dodge Lina J. Karam
+	Machine Learning as an Adversarial Service: Learning Black-Box Adversarial Examples.	2017	Jamie Hayes George Danezis
+	A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations	2017	Logan Engstrom Brandon Tran Dimitris Tsipras Ludwig Schmidt Aleksander Mądry
+	AutoAugment: Learning Augmentation Policies from Data	2018	Ekin D. Cubuk Barret Zoph Dandelion Mané Vijay Vasudevan Quoc V. Le
+	Evaluating and Understanding the Robustness of Adversarial Logit Pairing.	2018	Logan Engstrom Andrew Ilyas Anish Athalye
+	Playing the Game of Universal Adversarial Perturbations	2018	Julien Pérolat Mateusz Malinowski Bilal Piot Olivier Pietquin
+	ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness	2018	Robert Geirhos Patricia Rubisch Claudio Michaelis Matthias Bethge Felix A. Wichmann Wieland Brendel
+	Quantifying Perceptual Distortion of Adversarial Examples	2019	Matt Jordan Naren Sarayu Manoj Surbhi Goel Alexandros G. Dimakis
+	Transfer of Adversarial Robustness Between Perturbation Types	2019	Daniel Kang Yi Sun T. B. Brown Dan Hendrycks Jacob Steinhardt
+	Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation	2019	Raphael Gontijo Lopes Dong Yin Ben Poole Justin Gilmer Ekin D. Cubuk
+	Adversarial Examples Are a Natural Consequence of Test Error in Noise	2019	Nic Ford Justin Gilmer Nicolas Carlini Dogus Cubuk
+	Making Convolutional Networks Shift-Invariant Again	2019	Richard Zhang
+	Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming	2019	Claudio Michaelis Benjamin Mitzkus Robert Geirhos Evgenia Rusak Oliver Bringmann Alexander S. Ecker Matthias Bethge Wieland Brendel
+ PDF Chat	Feature Denoising for Improving Adversarial Robustness	2019	Cihang Xie Yuxin Wu Laurens van der Maaten Alan Yuille Kaiming He
+	Robustness of classifiers: from adversarial to random noise	2016	Alhussein Fawzi Seyed-Mohsen Moosavi-Dezfooli Pascal Frossard
+ PDF Chat	Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses	2019	Jérôme Rony Luiz G. Hafemann Luiz S. Oliveira Ismail Ben Ayed Robert Sabourin Éric Granger
+ PDF Chat	Exploring the Limits of Weakly Supervised Pretraining	2018	Dhruv Mahajan Ross Girshick Vignesh Ramanathan Kaiming He Manohar Paluri Yixuan Li Ashwin Bharambe Laurens van der Maaten
+ PDF Chat	Understanding how image quality affects deep neural networks	2016	Samuel Dodge Lina J. Karam
+	Towards Deep Learning Models Resistant to Adversarial Attacks.	2018	Aleksander Mądry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu
+	Adversarial training for free	2019	Ali Shafahi Mahyar Najibi Mohammad Ghiasi Zheng Xu John P. Dickerson Christoph Studer Larry S. Davis Gavin Taylor Tom Goldstein
+	A Fourier Perspective on Model Robustness in Computer Vision	2019	Dong Yin Raphael Gontijo Lopes Jonathon Shlens Ekin D. Cubuk Justin Gilmer
+ PDF Chat	Defending Against Universal Perturbations With Shared Adversarial Training	2019	Chaithanya Kumar Mummadi Thomas Brox Jan Hendrik Metzen
+ PDF Chat	Universal Adversarial Training	2020	Ali Shafahi Mahyar Najibi Zheng Xu J.W.T. Dickerson Larry S. Davis Tom Goldstein
+ PDF Chat	Self-Training With Noisy Student Improves ImageNet Classification	2020	Qizhe Xie Minh-Thang Luong Eduard Hovy Quoc V. Le
+	Fast Differentiable Clipping-Aware Normalization and Rescaling	2020	Jonas Rauber Matthias Bethge
+ PDF Chat	Achieving Generalizable Robustness of Deep Neural Networks by Stability Training	2019	Jan Laermann Wojciech Samek Nils Strodthoff