Semi-Supervised Semantic Segmentation 벤치마크
Semi-Supervised Semantic Segmentation on PASCAL Context 25% labeled
Validation mIoU
- 2019-08-15 — s4GAN+MLMT (DeepLab v2 ImageNet pre-trained): Validation mIoU 37.8
- 2021-06-29 — GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained): Validation mIoU 41.7
| Rank | Model | Validation mIoU | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | 41.7% | GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference | yh-pengtu/GuidedMix-Net | 2021 |
| 2 | s4GAN+MLMT (DeepLab v2 ImageNet pre-trained) | 37.8 | Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | sud0301/semisup-semseg | 2019 |
| 3 | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | 41.7% | GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference | yh-pengtu/GuidedMix-Net | 2021 |
| 4 | s4GAN+MLMT (DeepLab v2 ImageNet pre-trained) | 37.8 | Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | sud0301/semisup-semseg | 2019 |