Code and models for the paper Shape-Texture Debiased Neural Network Training (ICLR 2021)
☆111Aug 4, 2023Updated 2 years ago
Alternatives and similar repositories for ShapeTextureDebiasedTraining
Users that are interested in ShapeTextureDebiasedTraining are comparing it to the libraries listed below
Sorting:
- Code for our paper "Informative Dropout for Robust Representation Learning: A Shape-bias Perspective" (ICML 2020)☆125Dec 8, 2022Updated 3 years ago
- This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".☆46Nov 6, 2022Updated 3 years ago
- Source code for Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses (ECCV 2020)☆42Apr 2, 2019Updated 6 years ago
- Smooth Adversarial Training☆68Nov 16, 2020Updated 5 years ago
- Code for AutoNL on ImageNet (CVPR2020)☆104May 16, 2020Updated 5 years ago
- Source code for Learning Transferable Adversarial Examples via Ghost Networks (AAAI2020)☆58Feb 25, 2019Updated 7 years ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30May 16, 2022Updated 3 years ago
- ImageNet-R(endition) and DeepAugment (ICCV 2021)☆280Jul 23, 2021Updated 4 years ago
- [NeurIPS 2020] code for "Boundary thickness and robustness in learning models"☆20Dec 11, 2020Updated 5 years ago
- [NeurIPS'21] "AugMax: Adversarial Composition of Random Augmentations for Robust Training" by Haotao Wang, Chaowei Xiao, Jean Kossaifi, Z…☆125Dec 29, 2021Updated 4 years ago
- Batch Normalization with Enhanced Linear Transformation☆53Mar 13, 2024Updated 2 years ago
- Yet Another Pytorch Distributed MobileNetV2-based Networks Implementation☆63Apr 9, 2020Updated 5 years ago
- ☆107Jan 23, 2022Updated 4 years ago
- ☆19Mar 27, 2018Updated 7 years ago
- Project page for our paper: Interpreting Adversarially Trained Convolutional Neural Networks☆66Aug 8, 2019Updated 6 years ago
- A Closer Look at Accuracy vs. Robustness☆88May 17, 2021Updated 4 years ago
- [ICCV 2021] Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain☆80Sep 15, 2022Updated 3 years ago
- Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)