Clustered-patch Element Connection for Few-shot Learning

Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-5-shotRePRI (CECE-M,ResNet-50)#51Mean IoU: 46.9
few-shot-semantic-segmentation-on-coco-20i-5-shotRePRI (CECE-T,ResNet-50)#52Mean IoU: 46.7
few-shot-semantic-segmentation-on-coco-20i-1-shotRePRI (CECE-M,ResNet-50)#57Mean IoU: 38.3
few-shot-semantic-segmentation-on-coco-20i-1-shotRePRI (CECE-T,ResNet-50)#58Mean IoU: 38.1
few-shot-semantic-segmentation-on-pascal-5i-5-shotRePRI (CECE-M,ResNet-50)#67Mean IoU: 66.5
few-shot-semantic-segmentation-on-pascal-5i-5-shotRePRI (CECE-T,ResNet-50)#68Mean IoU: 66.2
few-shot-semantic-segmentation-on-pascal-5i-1-shotRePRI (CECE-T,ResNet-50)#75Mean IoU: 60.5
few-shot-semantic-segmentation-on-pascal-5i-1-shotRePRI (CECE-M,ResNet-50)#76Mean IoU: 60.4