hendrycks/robustness
Corruption and Perturbation Robustness (ICLR 2019)
Provides pre-built benchmark datasets (ImageNet-C, ImageNet-P, CIFAR-10-C/P) with 15 common corruptions and perturbations for systematically evaluating CNN robustness, alongside PyTorch evaluation code and a leaderboard tracking methods by mean Corruption Error (mCE) metric. Supports multiple scales from CIFAR to full ImageNet, with both static corruption variants and temporal perturbation sequences to measure consistency under distribution shift.
1,139 stars. No commits in the last 6 months.
Stars
1,139
Forks
151
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hendrycks/robustness"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
namkoong-lab/dro
A package of distributionally robust optimization (DRO) methods. Implemented via cvxpy and PyTorch
THUDM/grb
Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for...
neu-autonomy/nfl_veripy
Formal Verification of Neural Feedback Loops (NFLs)
MinghuiChen43/awesome-trustworthy-deep-learning
A curated list of trustworthy deep learning papers. Daily updating...
ADA-research/VERONA
A lightweight Python package for setting up robustness experiments and to compute robustness...