SimCLR (CoMatch)

Reported on 4 benchmarks across 2 tasks · 1 paper · 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 ClassificationonCIFAR-10, 80 Labels
Percentage error· 2020-11-23
5.98
best: 5 (MutexMatch (k=0.6C))
SOTA
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization arXiv:2011.11183
Semi-Supervised Image ClassificationonCIFAR-10, 80 Labels
Percentage error· 2020-11-23
5.98
best: 5 (MutexMatch (k=0.6C))
SOTA
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization arXiv:2011.11183
Image ClassificationonSTL-10, 1000 Labels
Accuracy· 2020-11-23
77.46
best: 94.53 (NP-Match)
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization arXiv:2011.11183
Semi-Supervised Image ClassificationonSTL-10, 1000 Labels
Accuracy· 2020-11-23
77.46
best: 94.53 (NP-Match)
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization arXiv:2011.11183