Masked Siamese Networks for Label-Efficient Learning

Open paper
Benchmark Model Rank Results
self-supervised-image-classification-on-imagenetMSN (ViT-L/7)#20Top 1 Accuracy: 80.7%Number of Params: 306M
semi-supervised-image-classification-on-imagenet-1-labeled-dataMSN (ViT-B/4)#9Top 1 Accuracy: 75.7%

Rank counts only results with a code link.