AI Paper Atlas

Research map / Benchmarks / CIFAR-100-C

CIFAR-100-C leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-100-C. Best accuracy: 77 (P-Shuffle / Uniform, NeurIPS 2022).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CIFAR-100-C · accuracy

16 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
177P-Shuffle / Uniform
ViT-B/16
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
NeurIPS 2022 · Appendix CIFAR-100 table
Recognition and long-tail
275.72RSPC-FAN-S-Hybrid
FAN-S-Hybrid
Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions
CVPR 2023 · Table 1
Attention and transformers
369.21MIRA+ROID
ResNeXt
MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation
NeurIPS 2026 · Plug-and-play table
Test-time adaptation
468.5BUFR
ResNet-18
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
ICLR 2022 · Object-recognition results tab
Domain adaptation and generalization
565.73Frob-SAM
ResNet18
A Universal Class of Sharpness-Aware Minimization Algorithms
ICML 2024 · Table 2
Implicit bias and generalization
659.75EATA + UniEnt
WideResNet-40-2
Unified Entropy Optimization for Open-Set Test-Time Adaptation
CVPR 2024 · Table 1
Test-time adaptation
757.98SK RegMixup
ResNet101
Tailoring Mixup to Data for Calibration
ICLR 2025 · Table 3
Recognition and long-tail
857.3ME-ADA
ResNeXt
Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
NeurIPS 2020 · Table 3
Certified and empirical robustness
956.7ClusT3
ResNet50
ClusT3: Information Invariant Test-Time Training
ICCV 2023 · Table 5
Test-time adaptation
1054.3TRUST
VMamba
TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
NeurIPS 2025 · Table: Top-1 classification ac
Test-time adaptation
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.