Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer

Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-pascal-voc-5-shotCWT (ResNet-50)#11Mean IoU: 66.5
few-shot-semantic-segmentation-on-coco-20i-pascal-voc-1-shotCWT (ResNet-50)#12Mean IoU: 59.5
few-shot-semantic-segmentation-on-coco-20i-5-shotCWT (ResNet-101)#59Mean IoU: 42
few-shot-semantic-segmentation-on-coco-20i-5-shotCWT (ResNet-50)#63Mean IoU: 41.3
few-shot-semantic-segmentation-on-coco-20i-1-shotCWT (ResNet-50)#69Mean IoU: 32.9
few-shot-semantic-segmentation-on-coco-20i-1-shotCWT (ResNet-101)#71Mean IoU: 32.4
few-shot-semantic-segmentation-on-pascal-5i-5-shotCWT (ResNet-101)#71Mean IoU: 64.7
few-shot-semantic-segmentation-on-pascal-5i-5-shotCWT (ResNet-50)#76Mean IoU: 63.7
few-shot-semantic-segmentation-on-pascal-5i-1-shotCWT (ResNet-101)#85Mean IoU: 58
few-shot-semantic-segmentation-on-pascal-5i-1-shotCWT (ResNet-50)#88Mean IoU: 56.4