|
MixMIM-L
|
MixMAE: Mixed and Masked Autoencoder for Efficien…
|
69.30
|
2022-05-26
|
|
|
SEER (RegNet10B - finetuned - 384px)
|
Vision Models Are More Robust And Fair When Pretr…
|
69.00
|
2022-02-16
|
|
|
MixMIM-B
|
MixMAE: Mixed and Masked Autoencoder for Efficien…
|
68.30
|
2022-05-26
|
|
|
MAE (ViT-H, 448)
|
Masked Autoencoders Are Scalable Vision Learners
|
66.80
|
2021-11-11
|
|
|
SEER
|
Self-supervised Pretraining of Visual Features in…
|
66.00
|
2021-03-02
|
|
|
SAMix (ResNet-50 Supervised)
|
Boosting Discriminative Visual Representation Lea…
|
64.30
|
2021-11-30
|
|
|
AutoMix (ResNet-50 Supervised)
|
AutoMix: Unveiling the Power of Mixup for Stronge…
|
64.10
|
2021-03-24
|
|
|
RegNetY-128GF (Supervised)
|
Self-supervised Pretraining of Visual Features in…
|
62.70
|
2021-03-02
|
|
|
BYOL
|
Bootstrap your own latent: A new approach to self…
|
54.00
|
2020-06-13
|
|
|
SimCLR
|
A Simple Framework for Contrastive Learning of Vi…
|
53.30
|
2020-02-13
|
|
|
MoCo v2
|
Improved Baselines with Momentum Contrastive Lear…
|
52.90
|
2020-03-09
|
|
|
InternImage-H
|
InternImage: Exploring Large-Scale Vision Foundat…
|
|
2022-11-10
|
|
|
SwAV
|
Unsupervised Learning of Visual Features by Contr…
|
|
2020-06-17
|
|
|
Barlow Twins (ResNet-50)
|
Barlow Twins: Self-Supervised Learning via Redund…
|
|
2021-03-04
|
|
|
ResNet-50 (Supervised)
|
Unsupervised Learning of Visual Features by Contr…
|
|
2020-06-17
|
|