Why do deep convolutional networks generalize so poorly to small image transformations?

30 May 2018

Papers citing "Why do deep convolutional networks generalize so poorly to small image transformations?"

50 / 79 papers shown

Title
Rotation Invariant Transformer for Recognizing Object in UAVs Shuo Chen Mang Ye Bo Du ViT 32 18 0 05 Nov 2023
Zone Evaluation: Revealing Spatial Bias in Object Detection Zhaohui Zheng Yuming Chen Qibin Hou Xiang Li Ping Wang Ming-Ming Cheng ObjD 24 3 0 20 Oct 2023
A New Multimodal Medical Image Fusion based on Laplacian Autoencoder with Channel Attention P. Wankhede M. Das Deep Gupta P. Radeva Ashwini M. Bakde MedIm 15 0 0 18 Oct 2023
OSNet & MNetO: Two Types of General Reconstruction Architectures for Linear Computed Tomography in Multi-Scenarios Zhisheng Wang Z. Deng Fenglin Liu Yixing Huang Haijun Yu Junning Cui 10 3 0 21 Sep 2023
Solving Large-scale Spatial Problems with Convolutional Neural Networks Damian Owerko Charilaos I. Kanatsoulis Alejandro Ribeiro 22 2 0 14 Jun 2023
Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits Zhuokai Zhao Takumi Matsuzawa W. Irvine Michael Maire G. Kindlmann 35 2 0 31 May 2023
Policy Gradient Methods in the Presence of Symmetries and State Abstractions Prakash Panangaden S. Rezaei-Shoshtari Rosie Zhao D. Meger Doina Precup 25 2 0 09 May 2023
Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations H. Michaeli T. Michaeli Daniel Soudry 21 14 0 14 Mar 2023
Steerable Equivariant Representation Learning Sangnie Bhardwaj Willie McClinton Tongzhou Wang Guillaume Lajoie Chen Sun Phillip Isola Dilip Krishnan OOD LLMSV 28 5 0 22 Feb 2023
Benchmarking performance of object detection under image distortions in an uncontrolled environment Ayman Beghdadi Malik Mallem Lotfi Beji 31 5 0 28 Oct 2022
Anisotropic multiresolution analyses for deepfake detection Wei Huang Michelangelo Valsecchi Michael Multerer AAML 24 5 0 26 Oct 2022
The Robustness Limits of SoTA Vision Models to Natural Variation Mark Ibrahim Q. Garrido Ari S. Morcos Diane Bouchacourt VLM 38 16 0 24 Oct 2022
Robust Self-Supervised Learning with Lie Groups Mark Ibrahim Diane Bouchacourt Ari S. Morcos SSL OOD 38 6 0 24 Oct 2022
The Lie Derivative for Measuring Learned Equivariance Nate Gruver Marc Finzi Micah Goldblum A. Wilson 16 34 0 06 Oct 2022
Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise Svetlana Pavlitskaya Joël Oswald J. Marius Zöllner NoLa AAML 22 5 0 27 Sep 2022
Frequency Dropout: Feature-Level Regularization via Randomized Filtering Mobarakol Islam Ben Glocker OOD 32 6 0 20 Sep 2022
Fairness and robustness in anti-causal prediction Maggie Makar Alexander DÁmour OOD 29 10 0 20 Sep 2022
On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks Hubert Leterme K. Polisano V. Perrier Alahari Karteek FAtt 38 2 0 19 Sep 2022
Shift Variance in Scene Text Detection M. Glitzner Jan-Hendrik Neudeck Philipp Härtinger 18 0 0 19 Aug 2022
Deep Neural Network Approximation of Invariant Functions through Dynamical Systems Qianxiao Li T. Lin Zuowei Shen 21 6 0 18 Aug 2022
Efficient CNN Architecture Design Guided by Visualization Liangqi Zhang Haibo Shen Yihao Luo Xiang Cao Leixilan Pan Tianjiang Wang Qi Feng 19 5 0 21 Jul 2022
Assaying Out-Of-Distribution Generalization in Transfer Learning F. Wenzel Andrea Dittadi Peter V. Gehler Carl-Johann Simon-Gabriel Max Horn ... Chris Russell Thomas Brox Bernt Schiele Bernhard Schölkopf Francesco Locatello OOD OODD AAML 51 71 0 19 Jul 2022
On the Strong Correlation Between Model Invariance and Generalization Weijian Deng Stephen Gould Liang Zheng OOD 32 16 0 14 Jul 2022
Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology Yunlong Zhang Yuxuan Sun Honglin Li S. Zheng Chenglu Zhu L. Yang OOD 56 27 0 30 Jun 2022
Saliency Map Based Data Augmentation Jalal Al-Afandi B. Magyar András Horváth 11 0 0 29 May 2022
Universum-inspired Supervised Contrastive Learning Aiyang Han Chuanxing Geng Songcan Chen SSL 23 3 0 22 Apr 2022
Domain Invariant Model with Graph Convolutional Network for Mammogram Classification Chu-ran Wang Jing Li Xinwei Sun Fandong Zhang Yizhou Yu Yizhou Wang MedIm OOD 30 2 0 21 Apr 2022
Feature robustness and sex differences in medical imaging: a case study in MRI-based Alzheimer's disease detection Eike Petersen Aasa Feragen Maria Luise da Costa Zemsch A. Henriksen Oskar Eiler Wiese Christensen M. Ganz OOD 16 27 0 04 Apr 2022
Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency Zhenhuan Liu Liang Li Huajie Jiang Xin Jin Dandan Tu Shuhui Wang Zhengjun Zha 21 7 0 02 Apr 2022
CapsNet for Medical Image Segmentation Minh-Trieu Tran Viet-Khoa Vo-Ho Kyle Quinn Hien Nguyen Khoa Luu Ngan Le MedIm 13 5 0 16 Mar 2022
Kubric: A scalable dataset generator Klaus Greff Francois Belletti Lucas Beyer Carl Doersch Yilun Du ... Ziyu Wang Tianhao Wu K. M. Yi Fangcheng Zhong Andrea Tagliasacchi 43 250 0 07 Mar 2022
Local Sliced-Wasserstein Feature Sets for Illumination-invariant Face Recognition Zhuang Yan Shiying Li M. Shifat-E.-Rabbi Xuwang Yin A. Rubaiyat Gustavo K. Rohde CVBM 27 7 0 22 Feb 2022
Feature-level augmentation to improve robustness of deep neural networks to affine transformations A. Sandru Mariana-Iuliana Georgescu Radu Tudor Ionescu OOD 16 3 0 10 Feb 2022
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks A. Harrington Arturo Deza OOD AAML 24 20 0 02 Feb 2022
Invariance encoding in sliced-Wasserstein space for image classification with limited training data M. Shifat-E.-Rabbi Yan Zhuang Shiying Li A. Rubaiyat Xuwang Yin Gustavo K. Rohde 17 9 0 09 Jan 2022
A generalization gap estimation for overparameterized models via the Langevin functional variance Akifumi Okuno Keisuke Yano 30 1 0 07 Dec 2021
Exploration into Translation-Equivariant Image Quantization W. Shin Gyubok Lee Jiyoung Lee Eun-Young Lyou Joonseok Lee E. Choi 33 7 0 01 Dec 2021
Wiggling Weights to Improve the Robustness of Classifiers Sadaf Gulshad Ivan Sosnovik A. Smeulders OOD 26 0 0 18 Nov 2021
Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks Lijia Yu Xiao-Shan Gao AAML 16 5 0 08 Nov 2021
AugMax: Adversarial Composition of Random Augmentations for Robust Training Haotao Wang Chaowei Xiao Jean Kossaifi Zhiding Yu Anima Anandkumar Zhangyang Wang 19 106 0 26 Oct 2021
Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans Ainaz Eftekhar Alexander Sax Roman Bachmann Jitendra Malik Amir Zamir MedIm 33 288 0 11 Oct 2021
Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function Md Tahmid Hossain S. Teng Ferdous Sohel Guojun Lu 49 13 0 03 Oct 2021
ML4ML: Automated Invariance Testing for Machine Learning Models Zukang Liao Pengfei Zhang Min Chen VLM 16 3 0 27 Sep 2021
Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling Zhendong Zhang OOD 13 5 0 24 Sep 2021
Shape-Biased Domain Generalization via Shock Graph Embeddings M. Narayanan Vickram Rajendran Benjamin Kimia 14 14 0 13 Sep 2021
Dead Pixel Test Using Effective Receptive Field Bum Jun Kim Hyeyeon Choi Hyeonah Jang Dong Gu Lee Wonseok Jeong Sang Woo Kim 19 25 0 31 Aug 2021
Toward Spatially Unbiased Generative Models Jooyoung Choi Jungbeom Lee Yonghyun Jeong Sungroh Yoon DiffM 30 17 0 03 Aug 2021
WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification Qiufu Li Linlin Shen Sheng Guo Zhihui Lai OOD 21 84 0 28 Jul 2021
Built-in Elastic Transformations for Improved Robustness Sadaf Gulshad Ivan Sosnovik A. Smeulders AAML 22 1 0 20 Jul 2021
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning Anders Andreassen Yasaman Bahri Behnam Neyshabur Rebecca Roelofs OOD OODD 24 78 0 30 Jun 2021