Feature-Proxy Transformer for Few-Shot Segmentation

Open paper
Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20iFPTrans (DeiT-B/16)#4Mean IoU: 69.7
few-shot-semantic-segmentation-on-coco-20iFPTrans (ViT-B/16)#7Mean IoU: 67.6
few-shot-semantic-segmentation-on-coco-20i-1FPTrans (DeiT-B/16)#17Mean IoU: 47
few-shot-semantic-segmentation-on-coco-20i-1FPTrans (ViT-B/16)#48Mean IoU: 42
few-shot-semantic-segmentation-on-coco-20i-2FPTrans (DeiT-B/16)#1Mean IoU: 79.3
few-shot-semantic-segmentation-on-coco-20i-2FPTrans (ViT-B/16)#4Mean IoU: 76.9
few-shot-semantic-segmentation-on-coco-20i-5FPTrans (DeiT-B/16)#5Mean IoU: 58.9
few-shot-semantic-segmentation-on-coco-20i-5FPTrans (ViT-B/16)#21Mean IoU: 53.8
few-shot-semantic-segmentation-on-pascal-5i-1FPTrans (DeiT-B/16)#13Mean IoU: 68.8
few-shot-semantic-segmentation-on-pascal-5i-1FPTrans (ViT-B/16)#45Mean IoU: 64.7
few-shot-semantic-segmentation-on-pascal-5i-5FPTrans (DeiT-B/16)#3Mean IoU: 78
few-shot-semantic-segmentation-on-pascal-5i-5FPTrans (ViT-B/16)#9Mean IoU: 73.7

Rank counts only results with a code link.