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

Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-10-shotRePRI (ResNet-50)#3Mean IoU: 44.1
few-shot-semantic-segmentation-on-pascal-5i-10-shotRePRI (ResNet-50)#3Mean IoU: 68.1
few-shot-semantic-segmentation-on-coco-20i-pascal-voc-5-shotRePRI (ResNet-50)#10Mean IoU: 67.7
few-shot-semantic-segmentation-on-coco-20i-pascal-voc-1-shotRePRI (ResNet-50)#11Mean IoU: 63.1
few-shot-semantic-segmentation-on-coco-20i-5-shotRePRI (ResNet-50)#60Mean IoU: 41.6
few-shot-semantic-segmentation-on-pascal-5i-5-shotRePRI (ResNet-50)#65Mean IoU: 66.6
few-shot-semantic-segmentation-on-pascal-5i-5-shotRePRI (ResNet-101)#70Mean IoU: 65.6
few-shot-semantic-segmentation-on-coco-20i-1-shotRePRI (ResNet-50)#67Mean IoU: 34.1
few-shot-semantic-segmentation-on-pascal-5i-1-shotRePRI (ResNet-50)#78Mean IoU: 59.7
few-shot-semantic-segmentation-on-pascal-5i-1-shotRePRI (ResNet-101)#80Mean IoU: 59.4