Efficient Adaption for CD-FSS through Knowledge Distillation
Pasquale De Marinis
pasqualedem
AI & ML interests
Computer Vision, Semantic Segmentation, Knowledge Distillation, Drones
Organizations
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 • 1 -
pasqualedem/label_anything_sam_1024_coco
0.1B • Updated • 41 -
pasqualedem/label_anything_256_sam_1024_coco
99.8M • Updated • 2 -
pasqualedem/label_anything_coco_fold0_mae_7a5p0t63
Image Segmentation • 95.3M • Updated • 6
Efficient Adaption for CD-FSS through Knowledge Distillation
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 • 1 -
pasqualedem/label_anything_sam_1024_coco
0.1B • Updated • 41 -
pasqualedem/label_anything_256_sam_1024_coco
99.8M • Updated • 2 -
pasqualedem/label_anything_coco_fold0_mae_7a5p0t63
Image Segmentation • 95.3M • Updated • 6