Datasets › ImageNet-C

ImageNet-C

Introduced by Dan Hendrycks et al. in Benchmarking Neural Network Robustness to Common Corruptions and Perturbations1 Jan 2019 archive 2025-07-28

ImageNet-C is an open source data set that consists of algorithmically generated corruptions (blur, noise) applied to the ImageNet test-set.

Source: Selective Brain Damage: Measuring the Disparate Impact of Model Pruning Image Source: https://arxiv.org/pdf/1807.01697.pdf

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
Domain Generalization	ImageNet-C	DINOv2 (ViT-g/14, frozen model, linear eval) mean Corruption Error (mCE) 28.2	DINOv2: Learning Robust Visual Features without Supervision	huggingface/transformers +25	47	Compare
Unsupervised Domain Adaptation	ImageNet-C	EfficientNet-L2+RPL mean Corruption Error (mCE) 22.0	If your data distribution shifts, use self-learning	bethgelab/robustness	16	Compare
Adversarial Robustness	ImageNet-C	DeiT-S (AdamW, Cosine) mean Corruption Error (mCE) 48.0	Are Transformers More Robust Than CNNs?	ytongbai/ViTs-vs-CNNs	4	Compare
Test-time Adaptation	ImageNet-C	DeYO Mean Accuracy 48.6	Entropy is not Enough for Test-Time Adaptation: From the...	Jhyun17/DeYO	1	Compare

Papers archive 2025-07-28

29 shown of 29 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 602. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
PushPull-Net: Inhibition-driven ResNet robust to image corruptions	1	1	7 Aug 2024	not harvested
Diffusion-Based Adaptation for Classification of Unknown Degraded Images	1	3	17 Jun 2024	not harvested
Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors	1	1	12 Mar 2024	ran 4 of 4 samples (0 unverified; 1 pointer-only for licence)
Fully Attentional Networks with Self-emerging Token Labeling	1	1	8 Jan 2024	not harvested
DINOv2: Learning Robust Visual Features without Supervision	26	4	14 Apr 2023	ran 21 of 46 samples (25 unverified; 12 pointer-only for licence)
MetaFormer Baselines for Vision	8	5	24 Oct 2022	ran 0 of 4 samples (4 unverified)
Generalized Parametric Contrastive Learning	4	1	26 Sep 2022	not harvested
Enhance the Visual Representation via Discrete Adversarial Training	1	1	16 Sep 2022	ran 10 of 11 samples (1 unverified; 1 pointer-only for licence)
Sequencer: Deep LSTM for Image Classification	5	1	4 May 2022	ran 4 of 9 samples (5 unverified)
Understanding The Robustness in Vision Transformers	2	3	26 Apr 2022	not harvested
Improving Vision Transformers by Revisiting High-frequency Components	1	1	3 Apr 2022	ran 10 of 14 samples (4 unverified)
A ConvNet for the 2020s	54	1	10 Jan 2022	ran 54 of 80 samples (26 unverified; 11 pointer-only for licence)
PRIME: A few primitives can boost robustness to common corruptions	1	3	27 Dec 2021	ran 5 of 8 samples (3 unverified)
Pyramid Adversarial Training Improves ViT Performance	1	2	30 Nov 2021	not harvested
Discrete Representations Strengthen Vision Transformer Robustness	1	3	20 Nov 2021	not harvested
Masked Autoencoders Are Scalable Vision Learners	58	1	11 Nov 2021	ran 71 of 137 samples (66 unverified; 73 pointer-only for licence)
Are Transformers More Robust Than CNNs?	1	4	10 Nov 2021	not harvested
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain	1	2	19 Aug 2021	ran 9 of 10 samples (1 unverified)
Global Filter Networks for Image Classification	4	1	1 Jul 2021	ran 6 of 10 samples (4 unverified; 5 pointer-only for licence)
Quality-Agnostic Image Recognition via Invertible Decoder	1	2	19 Jun 2021	not harvested
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations	2	3	3 Jun 2021	not harvested
Towards Robust Vision Transformer	2	3	17 May 2021	not harvested
If your data distribution shifts, use self-learning	1	10	27 Apr 2021	ran 2 of 2 samples (0 unverified)
Group-wise Inhibition based Feature Regularization for Robust Classification	1	1	3 Mar 2021	not harvested
Improving robustness against common corruptions by covariate shift adaptation	2	6	30 Jun 2020	ran 3 of 3 samples (0 unverified)
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization	1	1	29 Jun 2020	ran 13 of 14 samples (1 unverified)
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty	15	1	5 Dec 2019	ran 43 of 51 samples (8 unverified; 25 pointer-only for licence)
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations	14	1	28 Mar 2019	ran 2 of 3 samples (1 unverified)
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness	7	1	29 Nov 2018	ran 0 of 6 samples (6 unverified)

Dataset loaders archive 2025-07-28

torch-uncertainty.github.io/ENSTA-U2IS-AI/torch-uncertaintypytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Unsupervised Domain Adaptation Domain Generalization Adversarial Robustness Test-time Adaptation

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

Chinese

Variants archive 2025-07-28

ImageNet-C

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections