GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference

Benchmark Model Rank Results
semi-supervised-semantic-segmentation-on-1GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)#23Validation mIoU: 67.5%
semi-supervised-semantic-segmentation-on-10GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained)#16Validation mIoU: 73.7
semi-supervised-semantic-segmentation-on-15GuidedMix-Net(DeepLab v2 with ResNet101, input-size: 512x512 with multi-scale and flip, ImageNet pretrained)#6Validation mIoU: 78.2%
semi-supervised-semantic-segmentation-on-15GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)#9Validation mIoU: 76.5%
semi-supervised-semantic-segmentation-on-2GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)#24Validation mIoU: 65.8%
semi-supervised-semantic-segmentation-on-3GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)#8Validation mIoU: 56.9%
semi-supervised-semantic-segmentation-on-4GuidedMix-Net#15Validation mIoU: 76.4%
semi-supervised-semantic-segmentation-on-4GuidedMix-Net#22Validation mIoU: 73.4%
semi-supervised-semantic-segmentation-on-8GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)#19Validation mIoU: 69.8%
semi-supervised-semantic-segmentation-on-9GuidedMix-Net(DeepLab v2 with ResNet101, input-size: 512x512 with multi-scale and flip, ImageNet pretrained)#14Validation mIoU: 77.8%
semi-supervised-semantic-segmentation-on-9GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)#20Validation mIoU: 75.5%