Domain Generalization on ImageNet-Sketch

Metric: Top-1 accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Top-1 accuracy▼	Extra Data	Paper	Date↕	Code
1	Model soups (BASIC-L)	77.18	Yes	Model soups: averaging weights of multiple fine-...	2022-03-10	Code
2	Model soups (ViT-G/14)	74.24	Yes	Model soups: averaging weights of multiple fine-...	2022-03-10	Code
3	CAR-FT (CLIP, ViT-L/14@336px)	65.5	Yes	Context-Aware Robust Fine-Tuning	2022-11-29	-
4	ConvNeXt-XL (Im21k, 384)	55	Yes	A ConvNet for the 2020s	2022-01-10	Code
5	CAFormer-B36 (IN21K, 384)	54.5	Yes	MetaFormer Baselines for Vision	2022-10-24	Code
6	LLE (ViT-H/14, MAE, Edge Aug)	53.39	No	A Whac-A-Mole Dilemma: Shortcuts Come in Multipl...	2022-12-09	Code
7	ConvFormer-B36 (IN21K, 384)	52.9	Yes	MetaFormer Baselines for Vision	2022-10-24	Code
8	CAFormer-B36 (IN21K)	52.8	Yes	MetaFormer Baselines for Vision	2022-10-24	Code
9	ConvFormer-B36 (IN21K)	52.7	Yes	MetaFormer Baselines for Vision	2022-10-24	Code
10	MAE (ViT-H, 448)	50.9	No	Masked Autoencoders Are Scalable Vision Learners	2021-11-11	Code
11	MAE+DAT (ViT-H)	50.03	No	Enhance the Visual Representation via Discrete A...	2022-09-16	Code
12	GPaCo (ViT-L)	48.3	No	Generalized Parametric Contrastive Learning	2022-09-26	Code
13	Discrete Adversarial Distillation (ViT-B, 224)	46.1	No	Distilling Out-of-Distribution Robustness from V...	2023-11-02	Code
14	Pyramid Adversarial Training Improves ViT (Im21k)	46.03	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
15	SEER (RegNet10B)	45.6	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
16	DrViT	44.72	Yes	Discrete Representations Strengthen Vision Trans...	2021-11-20	Code
17	CAFormer-B36	42.5	No	MetaFormer Baselines for Vision	2022-10-24	Code
18	Pyramid Adversarial Training Improves ViT	41.04	No	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
19	ConvFormer-B36	39.5	No	MetaFormer Baselines for Vision	2022-10-24	Code
20	Sequencer2D-L	35.8	No	Sequencer: Deep LSTM for Image Classification	2022-05-04	Code

#1Model soups (BASIC-L)SOTA
77.18
Top-1 accuracy· Extra Data· 2022-03-10
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time Code
#2Model soups (ViT-G/14)
74.24
Top-1 accuracy· Extra Data· 2022-03-10
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time Code
#3CAR-FT (CLIP, ViT-L/14@336px)
65.5
Top-1 accuracy· Extra Data· 2022-11-29
Context-Aware Robust Fine-Tuning
#4ConvNeXt-XL (Im21k, 384)SOTA
55
Top-1 accuracy· Extra Data· 2022-01-10
A ConvNet for the 2020s Code
#5CAFormer-B36 (IN21K, 384)
54.5
Top-1 accuracy· Extra Data· 2022-10-24
MetaFormer Baselines for Vision Code
#6LLE (ViT-H/14, MAE, Edge Aug)
53.39
Top-1 accuracy· 2022-12-09
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others Code
#7ConvFormer-B36 (IN21K, 384)
52.9
Top-1 accuracy· Extra Data· 2022-10-24
MetaFormer Baselines for Vision Code
#8CAFormer-B36 (IN21K)
52.8
Top-1 accuracy· Extra Data· 2022-10-24
MetaFormer Baselines for Vision Code
#9ConvFormer-B36 (IN21K)
52.7
Top-1 accuracy· Extra Data· 2022-10-24
MetaFormer Baselines for Vision Code
#10MAE (ViT-H, 448)SOTA
50.9
Top-1 accuracy· 2021-11-11
Masked Autoencoders Are Scalable Vision Learners Code
#11MAE+DAT (ViT-H)
50.03
Top-1 accuracy· 2022-09-16
Enhance the Visual Representation via Discrete Adversarial Training Code
#12GPaCo (ViT-L)
48.3
Top-1 accuracy· 2022-09-26
Generalized Parametric Contrastive Learning Code
#13Discrete Adversarial Distillation (ViT-B, 224)
46.1
Top-1 accuracy· 2023-11-02
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models Code
#14Pyramid Adversarial Training Improves ViT (Im21k)
46.03
Top-1 accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#15SEER (RegNet10B)
45.6
Top-1 accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#16DrViT
44.72
Top-1 accuracy· Extra Data· 2021-11-20
Discrete Representations Strengthen Vision Transformer Robustness Code
#17CAFormer-B36
42.5
Top-1 accuracy· 2022-10-24
MetaFormer Baselines for Vision Code
#18Pyramid Adversarial Training Improves ViT
41.04
Top-1 accuracy· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#19ConvFormer-B36
39.5
Top-1 accuracy· 2022-10-24
MetaFormer Baselines for Vision Code
#20Sequencer2D-L
35.8
Top-1 accuracy· 2022-05-04
Sequencer: Deep LSTM for Image Classification Code