Prototype as Query for Few Shot Semantic Segmentation

Open paper
Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-1ProtoFormer (ResNet-101)#18Mean IoU: 47FB-IoU: 70
few-shot-semantic-segmentation-on-coco-20i-1ProtoFormer (ResNet-50)#29Mean IoU: 45.7FB-IoU: 69.6
few-shot-semantic-segmentation-on-coco-20i-5ProtoFormer (ResNet-101)#15Mean IoU: 54.7FB-IoU: 74.6
few-shot-semantic-segmentation-on-coco-20i-5ProtoFormer (ResNet-50)#22Mean IoU: 53.4FB-IoU: 73.3
few-shot-semantic-segmentation-on-pascal-5i-1ProtoFormer (ResNet-101)#58Mean IoU: 63.2FB-IoU: 72.6
few-shot-semantic-segmentation-on-pascal-5i-1ProtoFormer (ResNet-50)#59Mean IoU: 63.1FB-IoU: 72.6
few-shot-semantic-segmentation-on-pascal-5i-5ProtoFormer (ResNet-50)#53Mean IoU: 67.4FB-IoU: 77.1
few-shot-semantic-segmentation-on-pascal-5i-5ProtoFormer (ResNet-101)#55Mean IoU: 67FB-IoU: 76.3

Rank counts only results with a code link.