Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation

Benchmark Model Rank Results
few-shot-semantic-segmentation-on-coco-20i-5-shotQCLNet (ResNet-101)#26Mean IoU: 51.9
few-shot-semantic-segmentation-on-coco-20i-5-shotQCLNet (ResNet-50)#34Mean IoU: 50
few-shot-semantic-segmentation-on-pascal-5i-5-shotQCLNet (ResNet-101)#32Mean IoU: 71.2
few-shot-semantic-segmentation-on-pascal-5i-5-shotQCLNet (ResNet-50)#47Mean IoU: 69.5
few-shot-semantic-segmentation-on-pascal-5i-5-shotQCLNet (VGG-16)#73Mean IoU: 64.2
few-shot-semantic-segmentation-on-coco-20i-1-shotQCLNet (ResNet-101)#35Mean IoU: 43.6
few-shot-semantic-segmentation-on-coco-20i-1-shotQCLNet (ResNet-50)#45Mean IoU: 42.3
few-shot-semantic-segmentation-on-pascal-5i-1-shotQCLNet (ResNet-101)#35Mean IoU: 67
few-shot-semantic-segmentation-on-pascal-5i-1-shotQCLNet (ResNet-50)#60Mean IoU: 64.3
few-shot-semantic-segmentation-on-pascal-5i-1-shotQCLNet (VGG-16)#74Mean IoU: 60.6