Semi-supervised Vision Transformers at Scale

Open paper
Benchmark Model Rank Results
semi-supervised-image-classification-on-imagenet-1-labeled-dataSemi-ViT (ViT-Huge)#5Top 1 Accuracy: 80%Top 5 Accuracy: 93.1
semi-supervised-image-classification-on-imagenet-1-labeled-dataSemi-ViT (ViT-Large)#6Top 1 Accuracy: 77.3%
semi-supervised-image-classification-on-imagenet-1-labeled-dataSemi-ViT (ViT-Base)#15Top 1 Accuracy: 71%
semi-supervised-image-classification-on-imagenet-10-labeled-dataSemi-ViT (ViT-Huge)#4Top 1 Accuracy: 84.3%Top 5 Accuracy: 96.6%
semi-supervised-image-classification-on-imagenet-10-labeled-dataSemi-ViT (ViT-Large)#5Top 1 Accuracy: 83.3%
semi-supervised-image-classification-on-imagenet-10-labeled-dataSemi-ViT (ViT-Base)#10Top 1 Accuracy: 79.7%
semi-supervised-image-classification-on-imagenet-10-labeled-dataSemi-ViT (ViT-Small)#16Top 1 Accuracy: 77.1%

Rank counts only results with a code link.