Image Classification on Places205

Metric: Top 1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Top 1 Accuracy▼	Extra Data	Paper	Date↕	Code
1	MixMIM-L	69.3	No	MixMAE: Mixed and Masked Autoencoder for Efficie...	2022-05-26	Code
2	SEER (RegNet10B - finetuned - 384px)	69	Yes	Vision Models Are More Robust And Fair When Pret...	2022-02-16	Code
3	MixMIM-B	68.3	No	MixMAE: Mixed and Masked Autoencoder for Efficie...	2022-05-26	Code
4	MAE (ViT-H, 448)	66.8	No	Masked Autoencoders Are Scalable Vision Learners	2021-11-11	Code
5	SEER	66	No	Self-supervised Pretraining of Visual Features i...	2021-03-02	Code
6	SAMix (ResNet-50 Supervised)	64.3	No	Boosting Discriminative Visual Representation Le...	2021-11-30	Code
7	AutoMix (ResNet-50 Supervised)	64.1	No	AutoMix: Unveiling the Power of Mixup for Strong...	2021-03-24	Code
8	RegNetY-128GF (Supervised)	62.7	No	Self-supervised Pretraining of Visual Features i...	2021-03-02	Code
9	BYOL	54	No	Bootstrap your own latent: A new approach to sel...	2020-06-13	Code
10	SimCLR	53.3	No	A Simple Framework for Contrastive Learning of V...	2020-02-13	Code
11	MoCo v2	52.9	No	Improved Baselines with Momentum Contrastive Lea...	2020-03-09	Code

#1MixMIM-LSOTA
69.3
Top 1 Accuracy· 2022-05-26
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers Code
#2SEER (RegNet10B - finetuned - 384px)SOTA
69
Top 1 Accuracy· Extra Data· 2022-02-16
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Code
#3MixMIM-B
68.3
Top 1 Accuracy· 2022-05-26
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers Code
#4MAE (ViT-H, 448)SOTA
66.8
Top 1 Accuracy· 2021-11-11
Masked Autoencoders Are Scalable Vision Learners Code
#5SEERSOTA
66
Top 1 Accuracy· 2021-03-02
Self-supervised Pretraining of Visual Features in the Wild Code
#6SAMix (ResNet-50 Supervised)
64.3
Top 1 Accuracy· 2021-11-30
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup Code
#7AutoMix (ResNet-50 Supervised)
64.1
Top 1 Accuracy· 2021-03-24
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers Code
#8RegNetY-128GF (Supervised)
62.7
Top 1 Accuracy· 2021-03-02
Self-supervised Pretraining of Visual Features in the Wild Code
#9BYOLSOTA
54
Top 1 Accuracy· 2020-06-13
Bootstrap your own latent: A new approach to self-supervised Learning Code
#10SimCLRSOTA
53.3
Top 1 Accuracy· 2020-02-13
A Simple Framework for Contrastive Learning of Visual Representations Code
#11MoCo v2
52.9
Top 1 Accuracy· 2020-03-09
Improved Baselines with Momentum Contrastive Learning Code