model-robustness

[NeurIPS'21] "AugMax: Adversarial Composition of Random Augmentations for Robust Training" by Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Animashree Anandkumar, and Zhangyang Wang.

adversarial-learning normalization-techniques out-of-distribution model-robustness imagenet-c

UpdatedDec 29, 2021
Python

Jingkang50 /ICCV21_SCOOD

Star70

The Official Implementation of the ICCV-2021 Paper: Semantically Coherent Out-of-Distribution Detection.

computer-vision ood out-of-distribution out-of-distribution-detection model-robustness ood-detection

UpdatedMar 21, 2022
Python

wjun0830 /Localizable-Rotation

Star31

Official PyTorch Repository of "Tailoring Self-Supervision for Supervised Learning" (ECCV 2022 Paper)

deep-learning data-augmentation self-supervised-learning out-of-distribution-detection model-robustness long-tailed-recognition

UpdatedJul 28, 2023
Python

GATECH-EIC /Robust-Scratch-Ticket

Star13

[NeurIPS 2021] "Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks" by Yonggan Fu, Qixuan Yu, Yang Zhang, Shang Wu, Xu Ouyang, David Cox, Yingyan Lin

lottery-ticket-hypothesis model-robustness

UpdatedFeb 13, 2022
Python

amindadgar /adversarial-attacks-using-image-filters

Star4

This repository is an implementation ofhttps://link.springer.com/chapter/10.1007/978-3-030-72699-7_35 article. it uses evolutionary strategy (NSGA-II algorithm specificially) to configure image filters parameters in order to attack adversarially to a neural network.

tensorflow optimization keras cifar10 nsga-ii keras-tensorflow image-filters cifar-10 adversarial-attacks model-robustness pymoo

UpdatedFeb 11, 2023
Jupyter Notebook

nis-research /dfmX-augmentation

Star4

Augmentation for CV using frequency shortcuts

data-augmentation-strategies data-augmentation frequency-analysis fourier-transform robustness generalization adversarial-defense shortcut-learning model-robustness

UpdatedAug 13, 2023
Python

steventan0110 /NMTModelAttack

Star3

Code repository for the paper "Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation" with instructions to reproduce the results. Paper accepted by the conference of the Association for Machine Translation in the Americas (AMTA 2022)

machine-translation adversarial-attacks model-robustness