Running
on
T4
455
🎗️
Visual Understanding
Accurate & efficient vision models, ops and systems
-
-
Runtime error56📈
Matting Anything
-
shi-labs/oneformer_coco_swin_large
Image Segmentation • Updated • 104k • 2 -
shi-labs/oneformer_ade20k_swin_large
Image Segmentation • Updated • 39.2k • 14 -
shi-labs/oneformer_ade20k_swin_tiny
Image Segmentation • Updated • 187k • 12 -
shi-labs/oneformer_cityscapes_swin_large
Image Segmentation • Updated • 2.02k • 2 -
shi-labs/oneformer_ade20k_dinat_large
Image Segmentation • Updated • 5.77k • 9 -
shi-labs/oneformer_coco_dinat_large
Image Segmentation • Updated • 288 • 4 -
shi-labs/oneformer_cityscapes_dinat_large
Image Segmentation • Updated • 250 -
shi-labs/dinat-mini-in1k-224
Image Classification • Updated • 68 • 1 -
Neighborhood Attention Transformer
Paper • 2204.07143 • Published -
Dilated Neighborhood Attention Transformer
Paper • 2209.15001 • Published -
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
Paper • 2403.04690 • Published • 1 -
Matting Anything
Paper • 2306.05399 • Published • 6 -
OneFormer: One Transformer to Rule Universal Image Segmentation
Paper • 2211.06220 • Published