Semi Supervised Semantic Segmentation On 18
Metrics
Validation mIoU
Results
Performance results of various models on this benchmark
Model Name | Validation mIoU | Paper Title | Repository |
|---|---|---|---|
| S4GAN (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 50.48% | Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | |
| GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 53.51% | The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation | - |
| ClassMix (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 52.14% | ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning |
0 of 3 row(s) selected.