Label Anything performs multi-class few-shot semantic segmentation using visual prompts (bboxes, points, masks)
-
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts
Paper • 2407.02075 • Published -
pasqualedem/label_anything_sam_1024_coco
Updated • 315 -
pasqualedem/label_anything_256_sam_1024_coco
Updated • 7 -
pasqualedem/label_anything_coco_fold0_mae_7a5p0t63
Image Segmentation • Updated • 12
