Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

Open paper
Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20iRePRI (ResNet-50)#11Mean IoU: 63.1
few-shot-semantic-segmentation-on-coco-20i-1RePRI (ResNet-50)#67Mean IoU: 34.1
few-shot-semantic-segmentation-on-coco-20i-10RePRI (ResNet-50)#3Mean IoU: 44.1
few-shot-semantic-segmentation-on-coco-20i-2RePRI (ResNet-50)#10Mean IoU: 67.7
few-shot-semantic-segmentation-on-coco-20i-5RePRI (ResNet-50)#60Mean IoU: 41.6
few-shot-semantic-segmentation-on-pascal-5iRePRI (ResNet-50)#3Mean IoU: 68.1
few-shot-semantic-segmentation-on-pascal-5i-1RePRI (ResNet-50)#70Mean IoU: 59.7
few-shot-semantic-segmentation-on-pascal-5i-1RePRI (ResNet-101)#72Mean IoU: 59.4
few-shot-semantic-segmentation-on-pascal-5i-5RePRI (ResNet-50)#58Mean IoU: 66.6
few-shot-semantic-segmentation-on-pascal-5i-5RePRI (ResNet-101)#63Mean IoU: 65.6

Rank counts only results with a code link.