CoMatch + EPASS (ResNet-50)

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Computer Vision4 results

Image ClassificationonImageNet - 10% labeled data
Top 5 Accuracy· 2023-10-24
91.5
best: 92.6 (SimMatch + EPASS (ResNet-50))
Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector arXiv:2310.15764
Image ClassificationonImageNet - 1% labeled data
Top 5 Accuracy· 2023-10-24
87.3
best: 93.1 (Semi-ViT (ViT-Huge))
Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector arXiv:2310.15764
Semi-Supervised Image ClassificationonImageNet - 10% labeled data
Top 5 Accuracy· 2023-10-24
91.5
best: 92.6 (SimMatch + EPASS (ResNet-50))
Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector arXiv:2310.15764
Semi-Supervised Image ClassificationonImageNet - 1% labeled data
Top 5 Accuracy· 2023-10-24
87.3
best: 93.1 (Semi-ViT (ViT-Huge))
Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector arXiv:2310.15764