Masked Cross-image Encoding for Few-shot Segmentation

Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-1-shotMCE (ResNet-50)–Mean IoU: 44.22
few-shot-semantic-segmentation-on-coco-20i-5-shotMCE (ResNet-50)–Mean IoU: 51.04
few-shot-semantic-segmentation-on-pascal-5i-1-shotMCE (ResNet-50)–Mean IoU: 65.93FB-IoU: 78.1
few-shot-semantic-segmentation-on-pascal-5i-1-shotMCE (VGG-16)–Mean IoU: 62.87FB-IoU: 74.51
few-shot-semantic-segmentation-on-pascal-5i-5-shotMCE (ResNet-50)–Mean IoU: 70.03FB-IoU: 81.33
few-shot-semantic-segmentation-on-pascal-5i-5-shotMCE (VGG-16)–Mean IoU: 68.21FB-IoU: 78.2