Image Classification on OmniBenchmark

Metric: Average Top-1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Average Top-1 Accuracy▼	Extra Data	Paper	Date↕	Code
1	NOAH-ViTB/16	47.6	Yes	Neural Prompt Search	2022-06-09	Code
2	SwinTransformer	46.4	No	Swin Transformer: Hierarchical Vision Transforme...	2021-03-25	Code
3	Bamboo-R50	45.4	Yes	Bamboo: Building Mega-Scale Vision Dataset Conti...	2022-03-15	Code
4	Adapter-ViTB/16	44.5	Yes	Parameter-Efficient Transfer Learning for NLP	2019-02-02	Code
5	CLIP-RN50	42.1	Yes	Learning Transferable Visual Models From Natural...	2021-02-26	Code
6	IG-1B	40.4	Yes	Billion-scale semi-supervised learning for image...	2019-05-02	Code
7	BiT-M	40.4	Yes	Big Transfer (BiT): General Visual Representatio...	2019-12-24	Code
8	DINO	38.9	No	Emerging Properties in Self-Supervised Vision Tr...	2021-04-29	Code
9	SwAV	38.3	No	Unsupervised Learning of Visual Features by Cont...	2020-06-17	Code
10	ResNet-101	37.4	No	Deep Residual Learning for Image Recognition	2015-12-10	Code
11	MEAL-V2	36.6	No	MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-...	2020-09-17	Code
12	MoPro-V2	36.1	Yes	MoPro: Webly Supervised Learning with Momentum P...	2020-09-17	Code
13	EfficientNetB4	35.8	No	EfficientNet: Rethinking Model Scaling for Convo...	2019-05-28	Code
14	MoCoV2	34.8	No	Momentum Contrast for Unsupervised Visual Repres...	2019-11-13	Code
15	ResNet-50	34.3	No	Deep Residual Learning for Image Recognition	2015-12-10	Code
16	InceptionV4	32.3	No	Inception-v4, Inception-ResNet and the Impact of...	2016-02-23	Code
17	MLP-Mixer	32.2	No	MLP-Mixer: An all-MLP Architecture for Vision	2021-05-04	Code
18	Manifold	31.6	No	Manifold Mixup: Better Representations by Interp...	2018-06-13	Code
19	CutMix	31.1	No	CutMix: Regularization Strategy to Train Strong ...	2019-05-13	Code
20	ReLabel	30.8	No	Re-labeling ImageNet: from Single to Multi-Label...	2021-01-13	Code
21	MAE	30.6	No	Masked Autoencoders Are Scalable Vision Learners	2021-11-11	Code
22	BeiT	30.1	No	BEiT: BERT Pre-Training of Image Transformers	2021-06-15	Code

#1NOAH-ViTB/16SOTA
47.6
Average Top-1 Accuracy· Extra Data· 2022-06-09
Neural Prompt Search Code
#2SwinTransformerSOTA
46.4
Average Top-1 Accuracy· 2021-03-25
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Code
#3Bamboo-R50
45.4
Average Top-1 Accuracy· Extra Data· 2022-03-15
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy Code
#4Adapter-ViTB/16SOTA
44.5
Average Top-1 Accuracy· Extra Data· 2019-02-02
Parameter-Efficient Transfer Learning for NLP Code
#5CLIP-RN50
42.1
Average Top-1 Accuracy· Extra Data· 2021-02-26
Learning Transferable Visual Models From Natural Language Supervision Code
#6IG-1B
40.4
Average Top-1 Accuracy· Extra Data· 2019-05-02
Billion-scale semi-supervised learning for image classification Code
#7BiT-M
40.4
Average Top-1 Accuracy· Extra Data· 2019-12-24
Big Transfer (BiT): General Visual Representation Learning Code
#8DINO
38.9
Average Top-1 Accuracy· 2021-04-29
Emerging Properties in Self-Supervised Vision Transformers Code
#9SwAV
38.3
Average Top-1 Accuracy· 2020-06-17
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments Code
#10ResNet-101SOTA
37.4
Average Top-1 Accuracy· 2015-12-10
Deep Residual Learning for Image Recognition Code
#11MEAL-V2
36.6
Average Top-1 Accuracy· 2020-09-17
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks Code
#12MoPro-V2
36.1
Average Top-1 Accuracy· Extra Data· 2020-09-17
MoPro: Webly Supervised Learning with Momentum Prototypes Code
#13EfficientNetB4
35.8
Average Top-1 Accuracy· 2019-05-28
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Code
#14MoCoV2
34.8
Average Top-1 Accuracy· 2019-11-13
Momentum Contrast for Unsupervised Visual Representation Learning Code
#15ResNet-50
34.3
Average Top-1 Accuracy· 2015-12-10
Deep Residual Learning for Image Recognition Code
#16InceptionV4
32.3
Average Top-1 Accuracy· 2016-02-23
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning Code
#17MLP-Mixer
32.2
Average Top-1 Accuracy· 2021-05-04
MLP-Mixer: An all-MLP Architecture for Vision Code
#18Manifold
31.6
Average Top-1 Accuracy· 2018-06-13
Manifold Mixup: Better Representations by Interpolating Hidden States Code
#19CutMix
31.1
Average Top-1 Accuracy· 2019-05-13
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features Code
#20ReLabel
30.8
Average Top-1 Accuracy· 2021-01-13
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels Code
#21MAE
30.6
Average Top-1 Accuracy· 2021-11-11
Masked Autoencoders Are Scalable Vision Learners Code
#22BeiT
30.1
Average Top-1 Accuracy· 2021-06-15
BEiT: BERT Pre-Training of Image Transformers Code