Semi Supervised Semantic Segmentation On 19
Metriken
Validation mIoU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 59.98% | The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation |
| ClassMix (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 58.77% | ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning |
| S4GAN (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 55.61% | Semi-Supervised Semantic Segmentation with High- and Low-level Consistency |
0 of 3 row(s) selected.