Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector

Open paper
Benchmark Model Rank Results
semi-supervised-image-classification-on-imagenet-1-labeled-dataSimMatch + EPASS (ResNet-50)#19Top 1 Accuracy: 68.6%Top 5 Accuracy: 87.6
semi-supervised-image-classification-on-imagenet-1-labeled-dataCoMatch + EPASS (ResNet-50)#20Top 1 Accuracy: 67.4%Top 5 Accuracy: 87.3
semi-supervised-image-classification-on-imagenet-10-labeled-dataSimMatch + EPASS (ResNet-50)#22Top 1 Accuracy: 75.3%Top 5 Accuracy: 92.6
semi-supervised-image-classification-on-imagenet-10-labeled-dataCoMatch + EPASS (ResNet-50)#25Top 1 Accuracy: 74.1%Top 5 Accuracy: 91.5

Rank counts only results with a code link.