Image Classification on ObjectNet

Metric: Top-5 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Top-5 Accuracy▼	Extra Data	Paper	Date↕	Code
1	ViT-H/14	82.1	Yes	An Image is Worth 16x16 Words: Transformers for ...	2020-10-22	Code
2	BiT-L (ResNet-152x4)	80	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
3	AR-L (Opt Relevance)	73.5	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
4	AR-B (Opt Relevance)	70	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
5	BiT-M (ResNet-152x4)	69	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
6	AR-L	68.3	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
7	ViT-L (Opt Relevance)	65.8	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
8	ViT-B (Opt Relevance)	65.1	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
9	AR-B	63.7	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
10	AR-S (Opt Relevance)	61.7	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
11	ResNet-152 + GenInt with Transfer	61.43	Yes	Generative Interventions for Causal Learning	2020-12-22	Code
12	ViT-L	59.5	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
13	BiT-S (ResNet-152x4)	57	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
14	DeiT-L (Opt Relevance)	56.6	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
15	ViT-B	56.4	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
16	NASNet-A	56.05	Yes	-	-	-
17	AR-S	55.8	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
18	PNASNet-5L	54.95	Yes	-	-	-
19	DeiT-S (Opt Relevance)	53	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
20	Inception-v4	51.98	Yes	-	-	-
21	ResNet-50 + GroupNorm	50.2	Yes	Improving robustness against common corruptions ...	2020-06-30	Code
22	ResNet-50 + CGC	50.16	Yes	Context-Gated Convolution	2019-10-12	Code
23	ResNet-152	49.4	Yes	-	-	-
24	SeLa(v2) (reverse linear probing)	48.83	Yes	-	-	-
25	ResNet-50 + FixUp	48.6	Yes	Improving robustness against common corruptions ...	2020-06-30	Code
26	DeiT-L	48.5	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
27	ResNet-18 + GenInt with Transfer	48.02	Yes	Generative Interventions for Causal Learning	2020-12-22	Code
28	DeiT-S	47.3	Yes	Optimizing Relevance Maps of Vision Transformers...	2022-06-02	Code
29	DeepCluster(v2) (reverse linear probing)	46.81	Yes	-	-	-
30	SwAV (reverse linear probing)	43.64	Yes	-	-	-
31	VGG-14	37.15	Yes	-	-	-
32	OBoW (reverse linear probing)	31.72	Yes	-	-	-
33	MoCHi (reverse linear probing)	31.71	Yes	-	-	-
34	MoCo(v2) (reverse linear probing)	31.45	Yes	-	-	-
35	ResNet-152 (FRCNN-ag-ad, VOC)	29.7	Yes	Class-agnostic Object Detection	2020-11-28	-
36	AlexNet	17.6	Yes	-	-	-

#1ViT-H/14SOTA
82.1
Top-5 Accuracy· Extra Data· 2020-10-22
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Code
#2BiT-L (ResNet-152x4)SOTA
80
Top-5 Accuracy· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#3AR-L (Opt Relevance)
73.5
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#4AR-B (Opt Relevance)
70
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#5BiT-M (ResNet-152x4)
69
Top-5 Accuracy· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#6AR-L
68.3
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#7ViT-L (Opt Relevance)
65.8
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#8ViT-B (Opt Relevance)
65.1
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#9AR-B
63.7
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#10AR-S (Opt Relevance)
61.7
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#11ResNet-152 + GenInt with Transfer
61.43
Top-5 Accuracy· Extra Data· 2020-12-22
Generative Interventions for Causal Learning Code
#12ViT-L
59.5
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#13BiT-S (ResNet-152x4)
57
Top-5 Accuracy· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#14DeiT-L (Opt Relevance)
56.6
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#15ViT-B
56.4
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#16NASNet-A
56.05
Top-5 Accuracy· Extra Data
No paper
#17AR-S
55.8
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#18PNASNet-5L
54.95
Top-5 Accuracy· Extra Data
No paper
#19DeiT-S (Opt Relevance)
53
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#20Inception-v4
51.98
Top-5 Accuracy· Extra Data
No paper
#21ResNet-50 + GroupNorm
50.2
Top-5 Accuracy· Extra Data· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#22ResNet-50 + CGCSOTA
50.16
Top-5 Accuracy· Extra Data· 2019-10-12
Context-Gated Convolution Code
#23ResNet-152
49.4
Top-5 Accuracy· Extra Data
No paper
#24SeLa(v2) (reverse linear probing)
48.83
Top-5 Accuracy· Extra Data
No paper
#25ResNet-50 + FixUp
48.6
Top-5 Accuracy· Extra Data· 2020-06-30
Improving robustness against common corruptions by covariate shift adaptation Code
#26DeiT-L
48.5
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#27ResNet-18 + GenInt with Transfer
48.02
Top-5 Accuracy· Extra Data· 2020-12-22
Generative Interventions for Causal Learning Code
#28DeiT-S
47.3
Top-5 Accuracy· Extra Data· 2022-06-02
Optimizing Relevance Maps of Vision Transformers Improves Robustness Code
#29DeepCluster(v2) (reverse linear probing)
46.81
Top-5 Accuracy· Extra Data
No paper
#30SwAV (reverse linear probing)
43.64
Top-5 Accuracy· Extra Data
No paper
#31VGG-14
37.15
Top-5 Accuracy· Extra Data
No paper
#32OBoW (reverse linear probing)
31.72
Top-5 Accuracy· Extra Data
No paper
#33MoCHi (reverse linear probing)
31.71
Top-5 Accuracy· Extra Data
No paper
#34MoCo(v2) (reverse linear probing)
31.45
Top-5 Accuracy· Extra Data
No paper
#35ResNet-152 (FRCNN-ag-ad, VOC)
29.7
Top-5 Accuracy· Extra Data· 2020-11-28
Class-agnostic Object Detection
#36AlexNet
17.6
Top-5 Accuracy· Extra Data
No paper