SimCLR

Reported on 4 benchmarks across 2 tasks · 3 papers · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image ClassificationonCausal3DIdent
Accuracy · 2021-06-08
1
SOTA
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style arXiv:2106.04619
Image ClassificationonPlaces205
Top 1 Accuracy· 2020-02-13
53.3
best: 69.3 (MixMIM-L)
SOTA
A Simple Framework for Contrastive Learning of Visual Representations arXiv:2002.05709
Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2022-01-13
14.6
best: 82.7 (CoCa)
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?arXiv:2201.05119
Person Re-IdentificationonSYSU-30k
Rank-1· 2020-02-13
10.9
best: 36 (IICS (generalization))
A Simple Framework for Contrastive Learning of Visual Representations arXiv:2002.05709