Efficient Vision Transformers (ViT) models via soft-masked attention
-
XAFT/SM-Selective-ViT-Tiny-448
Image Classification • 5.84M • Updated • 1 -
XAFT/SM-Selective-ViT-Tiny-224
Image Classification • 5.72M • Updated • 1 -
XAFT/SM-Selective-ViT-Small-224-Distilled
Image Classification • 22.5M • Updated • 1 -
XAFT/SM-Selective-ViT-Small-224
Image Classification • 22.1M • Updated • 1