Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation

Benchmark Model Rank Results
generalized-few-shot-semantic-segmentation-on-coco-20i-1-shotPOP(ResNet-50)#2Mean Base and Novel: 35.01Mean IoU: 44.98
generalized-few-shot-semantic-segmentation-on-coco-20i-5-shotPOP(ResNet-50)#2Mean Base and Novel: 42.44Mean IoU: 48.75
generalized-few-shot-semantic-segmentation-on-pascal-5i-1-shotPOP(ResNet-50)#3Mean Base and Novel: 54.72Mean IoU: 64.77
generalized-few-shot-semantic-segmentation-on-pascal-5i-5-shotPOP(ResNet-50)#2Mean Base and Novel: 65.33Mean IoU: 70.28