Self-Calibrated Cross Attention Network for Few-Shot Segmentation

Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-5-shotSCCAN (ResNet-101)#10Mean IoU: 57FB-IoU: 74.8
few-shot-semantic-segmentation-on-coco-20i-5-shotSCCAN (ResNet-50)#19Mean IoU: 53.9FB-IoU: 74.2
few-shot-semantic-segmentation-on-coco-20i-1-shotSCCAN (ResNet-101)#14Mean IoU: 48.2FB-IoU: 69.7
few-shot-semantic-segmentation-on-coco-20i-1-shotSCCAN (ResNet-50)#25Mean IoU: 46.3FB-IoU: 69.9
few-shot-semantic-segmentation-on-pascal-5i-1-shotSCCAN (ResNet-101)#24Mean IoU: 68.3FB-IoU: 78.5
few-shot-semantic-segmentation-on-pascal-5i-1-shotSCCAN (ResNet-50)#39Mean IoU: 66.8FB-IoU: 77.7
few-shot-semantic-segmentation-on-pascal-5i-5-shotSCCAN (ResNet-101)#30Mean IoU: 71.5FB-IoU: 82.1
few-shot-semantic-segmentation-on-pascal-5i-5-shotSCCAN (ResNet-50)#42Mean IoU: 70.3FB-IoU: 81.8