Semantic Segmentation on PASCAL VOC 1/8 partition 2012 (blended high-quality)
0.819mIoUUniMatch
Evaluation Results
| Method | Links | |
|---|---|---|
| UniMatchBackbone=ResNet-101, Segmentation Framework=DeepLabv3+2023.10 | 0.819 | |
| Dual TeacherBackbone=ResNet-101, Segmentation Framework=DeepLabv3+, CutMix Variant=Original-CutMix2023.10 | 0.8147 | |
| AugSegBackbone=ResNet-101, Segmentation Framework=DeepLabv3+2023.10 | 0.8146 | |
| Dual TeacherBackbone=ResNet-101, Segmentation Framework=DeepLabv3+, CutMix Variant=Adaptive-CutMix2023.10 | 0.8119 | |
| Dual TeacherBackbone=ResNet-50, Segmentation Framework=DeepLabv3+, CutMix Variant=Original-CutMix2023.10 | 0.7959 | |
| Dual TeacherBackbone=ResNet-50, Segmentation Framework=DeepLabv3+, CutMix Variant=Adaptive-CutMix2023.10 | 0.7923 | |
| U2PLBackbone=ResNet-101, Segmentation Framework=DeepLabv3+2023.10 | 0.7901 | |
| UniMatchBackbone=ResNet-50, Segmentation Framework=DeepLabv3+2023.10 | 0.79 | |
| AugSegBackbone=ResNet-50, Segmentation Framework=DeepLabv3+2023.10 | 0.7827 | |
| U2PLBackbone=ResNet-50, Segmentation Framework=DeepLabv3+2023.10 | 0.774 | |
| Supervised-onlyBackbone=ResNet-101, Segmentation Framework=DeepLabv3+2023.10 | 0.75 | |
| Supervised-onlyBackbone=ResNet-50, Segmentation Framework=DeepLabv3+2023.10 | 0.719 |