Unsupervised Representation Learning by Balanced Self Attention Matching

Open paper
Benchmark Model Rank Results
self-supervised-image-classification-on-imagenetBAM (CAFormer-M36)#33Top 1 Accuracy: 79.3%
self-supervised-image-classification-on-imagenetBAM (ViT-B/16)#45Top 1 Accuracy: 78.1%Number of Params: 80M

Rank counts only results with a code link.