MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation

Open paper
Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-1MSANet (ResNet-101)#8Mean IoU: 50.45FB-IoU: 51.09
few-shot-semantic-segmentation-on-coco-20i-1MSANet (ResNet-50)#23Mean IoU: 46.44FB-IoU: 48.03
few-shot-semantic-segmentation-on-coco-20i-5MSANet (ResNet-101)#11Mean IoU: 56.3FB-IoU: 56.8
few-shot-semantic-segmentation-on-coco-20i-5MSANet (ResNet-50)#32Mean IoU: 50.47FB-IoU: 53.67
few-shot-semantic-segmentation-on-pascal-5i-1MSANet (ResNet-101)#10Mean IoU: 69.13FB-IoU: 80.38
few-shot-semantic-segmentation-on-pascal-5i-1MSANet (ResNet-50)#15Mean IoU: 68.52FB-IoU: 80.44
few-shot-semantic-segmentation-on-pascal-5i-1MSANet (VGG-16)#38Mean IoU: 65.76FB-IoU: 78.01
few-shot-semantic-segmentation-on-pascal-5i-5MSANet (ResNet-101)#8Mean IoU: 73.99FB-IoU: 84.3
few-shot-semantic-segmentation-on-pascal-5i-5MSANet (ResNet-50)#13Mean IoU: 72.6FB-IoU: 83.23
few-shot-semantic-segmentation-on-pascal-5i-5MSANet (VGG-16)#34Mean IoU: 70.4FB-IoU: 80.5

Rank counts only results with a code link.