Image Classification on ObjectNet

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	CoCa	82.7	Yes	CoCa: Contrastive Captioners are Image-Text Foun...	2022-05-04	Code
2	LiT	82.5	Yes	LiT: Zero-Shot Transfer with Locked-image text T...	2021-11-15	Code
3	BASIC	82.3	Yes	Combined Scaling for Zero-shot Transfer Learning	2021-11-19	-
4	EVA-02-CLIP-E/14+	79.6	Yes	EVA-CLIP: Improved Training Techniques for CLIP ...	2023-03-27	Code
5	Baseline (ViT-G/14)	79.03	Yes	Model soups: averaging weights of multiple fine-...	2022-03-10	Code
6	Model soups (ViT-G/14)	78.52	Yes	Model soups: averaging weights of multiple fine-...	2022-03-10	Code
7	MAWS (ViT-6.5B)	77.9	Yes	The effectiveness of MAE pre-pretraining for bil...	2023-03-23	Code
8	MAWS (ViT-2B)	75.8	Yes	The effectiveness of MAE pre-pretraining for bil...	2023-03-23	Code
9	MAWS (ViT-H)	72.6	Yes	The effectiveness of MAE pre-pretraining for bil...	2023-03-23	Code
10	CLIP	72.3	Yes	Learning Transferable Visual Models From Natural...	2021-02-26	Code
11	ALIGN	72.2	Yes	Combined Scaling for Zero-shot Transfer Learning	2021-11-19	-
12	WiSE-FT	72.1	Yes	Robust fine-tuning of zero-shot models	2021-09-04	Code
13	ViT-e	72	No	PaLI: A Jointly-Scaled Multilingual Language-Ima...	2022-09-14	Code
14	ViT-G/14	70.53	Yes	Scaling Vision Transformers	2021-06-08	Code
15	SWAG (ViT H/14)	69.5	Yes	Revisiting Weakly Supervised Pre-Training of Vis...	2022-01-20	Code
16	NS (Eff.-L2)	68.5	Yes	Scaling Vision Transformers	2021-06-08	Code
17	RegNetY 128GF (Platt)	64.3	Yes	Revisiting Weakly Supervised Pre-Training of Vis...	2022-01-20	Code
18	LLE (ViT-H/14, MAE, Edge Aug)	60.78	No	A Whac-A-Mole Dilemma: Shortcuts Come in Multipl...	2022-12-09	Code
19	SEER (RegNet10B)	60.2	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
20	ViT H/14 (Platt)	60	Yes	Revisiting Weakly Supervised Pre-Training of Vis...	2022-01-20	Code
21	BiT-L (ResNet-152x4)	58.7	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
22	ViT L/16 (Platt)	57.3	Yes	Revisiting Weakly Supervised Pre-Training of Vis...	2022-01-20	Code
23	Vit B/16 (Bamboo)	53.9	Yes	Bamboo: Building Mega-Scale Vision Dataset Conti...	2022-03-15	Code
24	AR-L (Opt Relevance)	52	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
25	ALIGN-MRL	51.6	Yes	Matryoshka Representation Learning	2022-05-26	Code
26	ViT-B/16 (ANN-1.3B)	50.7	Yes	Billion-Scale Pretraining with Vision Transforme...	2021-08-12	-
27	ViT-B/16 (512x512) + Pyramid	49.39	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
28	ResNet-101 (JFT-300M)	49.1	Yes	Billion-Scale Pretraining with Vision Transforme...	2021-08-12	-
29	ViT B/16	48.9	Yes	Revisiting Weakly Supervised Pre-Training of Vis...	2022-01-20	Code
30	ViT-B/32	48.4	Yes	Billion-Scale Pretraining with Vision Transforme...	2021-08-12	-
31	ViT-B/16 (512x512) + Pixel	47.53	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
32	AR-B (Opt Relevance)	47.1	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
33	BiT-M (ResNet-152x4)	47	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
34	ViT-B/16 (512x512)	46.68	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
35	ViT-B (Discrete 512x512)	46.62	Yes	Discrete Representations Strengthen Vision Trans...	2021-11-20	Code
36	AR-L	46.5	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
37	ViT-L (Opt Relevance)	43.2	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
38	CLIP L	42.8	Yes	Optimal Representations for Covariate Shift	2021-12-31	Code
39	ResNet-50 (JFT-300M)	42.5	Yes	Billion-Scale Pretraining with Vision Transforme...	2021-08-12	-
40	ViT-B (Opt Relevance)	42.2	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
41	CLIP L (LAION)	42.1	Yes	Optimal Representations for Covariate Shift	2021-12-31	Code
42	AR-B	41.4	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
43	RegViT on 384x384 + Adv Pyramid	39.79	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
44	ResNet-152 + GenInt with Transfer	39.38	Yes	Generative Interventions for Causal Learning	2020-12-22	Code
45	AR-S (Opt Relevance)	39.3	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
46	ResNet-50 (Bamboo)	38.8	Yes	Bamboo: Building Mega-Scale Vision Dataset Conti...	2022-03-15	Code
47	RegViT on 384x384 + Adv Pixel	37.41	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
48	ViT-L	37.4	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
49	DeiT-L (Opt Relevance)	36.3	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
50	BiT-S (ResNet-152x4)	36	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
51	NASNet-A	35.77	Yes	-	-	-
52	PNASNet-5L	35.63	Yes	-	-	-
53	RegViT on 384x384	35.59	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
54	ViT-B	35.1	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
55	RegViT on 384x384 + Random Pyramid	34.83	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
56	AR-S	34.3	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
57	RegViT on 384x384 + Random Pixel	34.12	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
58	RegViT (RandAug) + Adv Pyramid	32.92	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
59	Inception-v4	32.24	Yes	-	-	-
60	DeiT-S (Opt Relevance)	31.6	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
61	ResNet-50 + CGC	31.53	Yes	Context-Gated Convolution	2019-10-12	Code
62	DeiT-L	31.4	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
63	Discrete ViT + Pixel	30.98	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
64	Discrete ViT + Pyramid	30.28	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
65	RegViT (RandAug) + Adv Pixel	30.11	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
66	Discrete ViT	29.95	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
67	ResNet-152	29.59	Yes	-	-	-
68	RegViT (RandAug) + Random Pyramid	29.41	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
69	RegViT (RandAug)	29.3	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
70	ResNet-50 + GroupNorm	29.2	Yes	Improving robustness against common corruptions ...	2020-06-30	Code
71	ResNet-50 + RoHL	29.2	Yes	Improving robustness against common corruptions ...	2020-06-30	Code
72	RegViT (RandAug) + Random Pixel	28.72	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
73	MLP-Mixer + Pyramid	28.6	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
74	ResNet-50 + FixUp	28.5	Yes	Improving robustness against common corruptions ...	2020-06-30	Code
75	ResNet-50 + MixUp (rescaled)	28.37	Yes	On Mixup Regularization	2020-06-10	Code
76	DeiT-S	28.3	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
77	ResNet-18 + GenInt with Transfer	27.03	Yes	Generative Interventions for Causal Learning	2020-12-22	Code
78	MLP-Mixer	25.9	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
79	RELICv2	25.9	Yes	Pushing the limits of self-supervised ResNets: C...	2022-01-13	Code
80	ViT + MixUp	25.65	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
81	C-BYOL	25.5	Yes	Compressive Visual Representations	2021-09-27	Code
82	MLP-Mixer + Pixel	24.75	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
83	BYOL (BG_RM)	23.9	Yes	Characterizing and Improving the Robustness of S...	2021-03-23	-
84	RELIC	23.8	Yes	Pushing the limits of self-supervised ResNets: C...	2022-01-13	Code
85	BYOL	23	Yes	Pushing the limits of self-supervised ResNets: C...	2022-01-13	Code
86	SwAV (BG_RM)	21.9	Yes	Characterizing and Improving the Robustness of S...	2021-03-23	-
87	ViT + CutMix	21.61	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
88	MoCo-v2 (BG_Swaps)	20.8	Yes	Characterizing and Improving the Robustness of S...	2021-03-23	-
89	C-SimCLR	20.8	Yes	Compressive Visual Representations	2021-09-27	Code
90	SeLa(v2) (reverse linear probing)	20.61	Yes	-	-	-
91	DILEMMA	20.51	Yes	Representation Learning by Detecting Incorrect L...	2022-04-10	Code
92	DeepCluster(v2) (reverse linear probing)	19.73	Yes	-	-	-
93	VGG-14	19.13	Yes	-	-	-
94	ResNet-50 (ImageNet-Captions)	18.7	Yes	Data Determines Distributional Robustness in Con...	2022-05-03	Code
95	SwAV (reverse linear probing)	17.71	Yes	-	-	-
96	ViT	17.36	Yes	Pyramid Adversarial Training Improves ViT Perfor...	2021-11-30	Code
97	ResNet34-RPG	16.5	Yes	Compact and Optimal Deep Learning with Recurrent...	2021-07-15	Code
98	CLIP (CC12M pretrain)	15.24	Yes	Robust Cross-Modal Representation Learning with ...	2022-04-10	-
99	SimCLR	14.6	Yes	Pushing the limits of self-supervised ResNets: C...	2022-01-13	Code
100	ResNet-152 (FRCNN-ag-ad, VOC)	13.2	Yes	Class-agnostic Object Detection	2020-11-28	-
101	MoCo(v2) (reverse linear probing)	12.67	Yes	-	-	-
102	MoCHi (reverse linear probing)	12.64	Yes	-	-	-
103	OBoW (reverse linear probing)	12.23	Yes	-	-	-
104	AlexNet	6.78	Yes	-	-	-
105	BigBiGAN (RevNet-50 4×)	4.92	Yes	Self-Supervised Learning for Large-Scale Unsuper...	2020-08-24	Code

#1CoCaSOTA
82.7
Top-1 Accuracy· Extra Data· 2022-05-04
CoCa: Contrastive Captioners are Image-Text Foundation Models Code
#2LiTSOTA
82.5
Top-1 Accuracy· Extra Data· 2021-11-15
LiT: Zero-Shot Transfer with Locked-image text Tuning Code
#3BASIC
82.3
Top-1 Accuracy· Extra Data· 2021-11-19
Combined Scaling for Zero-shot Transfer Learning
#4EVA-02-CLIP-E/14+
79.6
Top-1 Accuracy· Extra Data· 2023-03-27
EVA-CLIP: Improved Training Techniques for CLIP at Scale Code
#5Baseline (ViT-G/14)
79.03
Top-1 Accuracy· Extra Data· 2022-03-10
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time Code
#6Model soups (ViT-G/14)
78.52
Top-1 Accuracy· Extra Data· 2022-03-10
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time Code
#7MAWS (ViT-6.5B)
77.9
Top-1 Accuracy· Extra Data· 2023-03-23
The effectiveness of MAE pre-pretraining for billion-scale pretraining Code
#8MAWS (ViT-2B)
75.8
Top-1 Accuracy· Extra Data· 2023-03-23
The effectiveness of MAE pre-pretraining for billion-scale pretraining Code
#9MAWS (ViT-H)
72.6
Top-1 Accuracy· Extra Data· 2023-03-23
The effectiveness of MAE pre-pretraining for billion-scale pretraining Code
#10CLIPSOTA
72.3
Top-1 Accuracy· Extra Data· 2021-02-26
Learning Transferable Visual Models From Natural Language Supervision Code
#11ALIGN
72.2
Top-1 Accuracy· Extra Data· 2021-11-19
Combined Scaling for Zero-shot Transfer Learning
#12WiSE-FT
72.1
Top-1 Accuracy· Extra Data· 2021-09-04
Robust fine-tuning of zero-shot models Code
#13ViT-e
72
Top-1 Accuracy· 2022-09-14
PaLI: A Jointly-Scaled Multilingual Language-Image Model Code
#14ViT-G/14
70.53
Top-1 Accuracy· Extra Data· 2021-06-08
Scaling Vision Transformers Code
#15SWAG (ViT H/14)
69.5
Top-1 Accuracy· Extra Data· 2022-01-20
Revisiting Weakly Supervised Pre-Training of Visual Perception Models Code
#16NS (Eff.-L2)
68.5
Top-1 Accuracy· Extra Data· 2021-06-08
Scaling Vision Transformers Code
#17RegNetY 128GF (Platt)
64.3
Top-1 Accuracy· Extra Data· 2022-01-20
Revisiting Weakly Supervised Pre-Training of Visual Perception Models Code
#18LLE (ViT-H/14, MAE, Edge Aug)
60.78
Top-1 Accuracy· 2022-12-09
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others Code
#19SEER (RegNet10B)
60.2
Top-1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#20ViT H/14 (Platt)
60
Top-1 Accuracy· Extra Data· 2022-01-20
Revisiting Weakly Supervised Pre-Training of Visual Perception Models Code
#21BiT-L (ResNet-152x4)SOTA
58.7
Top-1 Accuracy· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#22ViT L/16 (Platt)
57.3
Top-1 Accuracy· Extra Data· 2022-01-20
Revisiting Weakly Supervised Pre-Training of Visual Perception Models Code
#23Vit B/16 (Bamboo)
53.9
Top-1 Accuracy· Extra Data· 2022-03-15
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy Code
#24AR-L (Opt Relevance)
52
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#25ALIGN-MRL
51.6
Top-1 Accuracy· Extra Data· 2022-05-26
Matryoshka Representation Learning Code
#26ViT-B/16 (ANN-1.3B)
50.7
Top-1 Accuracy· Extra Data· 2021-08-12
Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
#27ViT-B/16 (512x512) + Pyramid
49.39
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#28ResNet-101 (JFT-300M)
49.1
Top-1 Accuracy· Extra Data· 2021-08-12
Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
#29ViT B/16
48.9
Top-1 Accuracy· Extra Data· 2022-01-20
Revisiting Weakly Supervised Pre-Training of Visual Perception Models Code
#30ViT-B/32
48.4
Top-1 Accuracy· Extra Data· 2021-08-12
Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
#31ViT-B/16 (512x512) + Pixel
47.53
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#32AR-B (Opt Relevance)
47.1
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#33BiT-M (ResNet-152x4)
47
Top-1 Accuracy· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#34ViT-B/16 (512x512)
46.68
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#35ViT-B (Discrete 512x512)
46.62
Top-1 Accuracy· Extra Data· 2021-11-20
Discrete Representations Strengthen Vision Transformer Robustness Code
#36AR-L
46.5
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#37ViT-L (Opt Relevance)
43.2
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#38CLIP L
42.8
Top-1 Accuracy· Extra Data· 2021-12-31
Optimal Representations for Covariate Shift Code
#39ResNet-50 (JFT-300M)
42.5
Top-1 Accuracy· Extra Data· 2021-08-12
Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
#40ViT-B (Opt Relevance)
42.2
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#41CLIP L (LAION)
42.1
Top-1 Accuracy· Extra Data· 2021-12-31
Optimal Representations for Covariate Shift Code
#42AR-B
41.4
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#43RegViT on 384x384 + Adv Pyramid
39.79
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#44ResNet-152 + GenInt with Transfer
39.38
Top-1 Accuracy· Extra Data· 2020-12-22
Generative Interventions for Causal Learning Code
#45AR-S (Opt Relevance)
39.3
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#46ResNet-50 (Bamboo)
38.8
Top-1 Accuracy· Extra Data· 2022-03-15
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy Code
#47RegViT on 384x384 + Adv Pixel
37.41
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#48ViT-L
37.4
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#49DeiT-L (Opt Relevance)
36.3
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#50BiT-S (ResNet-152x4)
36
Top-1 Accuracy· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#51NASNet-A
35.77
Top-1 Accuracy· Extra Data
No paper
#52PNASNet-5L
35.63
Top-1 Accuracy· Extra Data
No paper
#53RegViT on 384x384
35.59
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#54ViT-B
35.1
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#55RegViT on 384x384 + Random Pyramid
34.83
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#56AR-S
34.3
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#57RegViT on 384x384 + Random Pixel
34.12
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#58RegViT (RandAug) + Adv Pyramid
32.92
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#59Inception-v4
32.24
Top-1 Accuracy· Extra Data
No paper
#60DeiT-S (Opt Relevance)
31.6
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#61ResNet-50 + CGCSOTA
31.53
Top-1 Accuracy· Extra Data· 2019-10-12
Context-Gated Convolution Code
#62DeiT-L
31.4
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#63Discrete ViT + Pixel
30.98
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#64Discrete ViT + Pyramid
30.28
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#65RegViT (RandAug) + Adv Pixel
30.11
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#66Discrete ViT
29.95
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#67ResNet-152
29.59
Top-1 Accuracy· Extra Data
No paper
#68RegViT (RandAug) + Random Pyramid
29.41
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#69RegViT (RandAug)
29.3
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#70ResNet-50 + GroupNorm
29.2
Top-1 Accuracy· Extra Data· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#71ResNet-50 + RoHL
29.2
Top-1 Accuracy· Extra Data· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#72RegViT (RandAug) + Random Pixel
28.72
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#73MLP-Mixer + Pyramid
28.6
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#74ResNet-50 + FixUp
28.5
Top-1 Accuracy· Extra Data· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#75ResNet-50 + MixUp (rescaled)
28.37
Top-1 Accuracy· Extra Data· 2020-06-10
On Mixup Regularization Code
#76DeiT-S
28.3
Top-1 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#77ResNet-18 + GenInt with Transfer
27.03
Top-1 Accuracy· Extra Data· 2020-12-22
Generative Interventions for Causal Learning Code
#78MLP-Mixer
25.9
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#79RELICv2
25.9
Top-1 Accuracy· Extra Data· 2022-01-13
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?Code
#80ViT + MixUp
25.65
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#81C-BYOL
25.5
Top-1 Accuracy· Extra Data· 2021-09-27
Compressive Visual Representations Code
#82MLP-Mixer + Pixel
24.75
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#83BYOL (BG_RM)
23.9
Top-1 Accuracy· Extra Data· 2021-03-23
Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations
#84RELIC
23.8
Top-1 Accuracy· Extra Data· 2022-01-13
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?Code
#85BYOL
23
Top-1 Accuracy· Extra Data· 2022-01-13
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?Code
#86SwAV (BG_RM)
21.9
Top-1 Accuracy· Extra Data· 2021-03-23
Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations
#87ViT + CutMix
21.61
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#88MoCo-v2 (BG_Swaps)
20.8
Top-1 Accuracy· Extra Data· 2021-03-23
Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations
#89C-SimCLR
20.8
Top-1 Accuracy· Extra Data· 2021-09-27
Compressive Visual Representations Code
#90SeLa(v2) (reverse linear probing)
20.61
Top-1 Accuracy· Extra Data
No paper
#91DILEMMA
20.51
Top-1 Accuracy· Extra Data· 2022-04-10
Representation Learning by Detecting Incorrect Location Embeddings Code
#92DeepCluster(v2) (reverse linear probing)
19.73
Top-1 Accuracy· Extra Data
No paper
#93VGG-14
19.13
Top-1 Accuracy· Extra Data
No paper
#94ResNet-50 (ImageNet-Captions)
18.7
Top-1 Accuracy· Extra Data· 2022-05-03
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)Code
#95SwAV (reverse linear probing)
17.71
Top-1 Accuracy· Extra Data
No paper
#96ViT
17.36
Top-1 Accuracy· Extra Data· 2021-11-30
Pyramid Adversarial Training Improves ViT Performance Code
#97ResNet34-RPG
16.5
Top-1 Accuracy· Extra Data· 2021-07-15
Compact and Optimal Deep Learning with Recurrent Parameter Generators Code
#98CLIP (CC12M pretrain)
15.24
Top-1 Accuracy· Extra Data· 2022-04-10
Robust Cross-Modal Representation Learning with Progressive Self-Distillation
#99SimCLR
14.6
Top-1 Accuracy· Extra Data· 2022-01-13
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?Code
#100ResNet-152 (FRCNN-ag-ad, VOC)
13.2
Top-1 Accuracy· Extra Data· 2020-11-28
Class-agnostic Object Detection
#101MoCo(v2) (reverse linear probing)
12.67
Top-1 Accuracy· Extra Data
No paper
#102MoCHi (reverse linear probing)
12.64
Top-1 Accuracy· Extra Data
No paper
#103OBoW (reverse linear probing)
12.23
Top-1 Accuracy· Extra Data
No paper
#104AlexNet
6.78
Top-1 Accuracy· Extra Data
No paper
#105BigBiGAN (RevNet-50 4×)
4.92
Top-1 Accuracy· Extra Data· 2020-08-24
Self-Supervised Learning for Large-Scale Unsupervised Image Clustering Code