| Bootstrapping Semantic Segmentation with Regional Contrast | ✓ Link | 73.66% | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained) | 2021-04-09 |
| Semi-supervised Semantic Segmentation with Error Localization Network | ✓ Link | 72.52% | Error Localization Network (DeeplabV3 with ResNet-101) | 2022-04-05 |
| Semi-supervised Semantic Segmentation with Error Localization Network | ✓ Link | 70.52% | Error Localization Network (DeeplabV3 with ResNet-50) | 2022-04-05 |
| Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank | ✓ Link | 70.0% | SemiSegContrast
(DeepLab v2 with ResNet-101 backbone, MSCOCO pretrained) | 2021-04-27 |
| DMT: Dynamic Mutual Training for Semi-Supervised Learning | ✓ Link | 69.92% | DMT (DeepLab v2 MSCOCO/ImageNet pre-trained) | 2020-04-18 |
| Semi-supervised semantic segmentation needs strong, varied perturbations | ✓ Link | 69.57% | CutMix (DeepLab v3+ ImageNet pre-trained) | 2019-06-05 |
| The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation | | 69.40% | GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 2021-03-31 |
| Bootstrapping Semantic Segmentation with Regional Contrast | ✓ Link | 68.85% | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | 2021-04-09 |
| ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning | ✓ Link | 67.77% | ClassMix (DeepLab v2 MSCOCO pretrained) | 2020-07-15 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 67.2% | s4GAN + MLMT (DeepLab v2 MSCOCO/ImageNet pre-trained) | 2019-08-15 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 66.6% | s4GAN+MLMT (DeepLab v3+ ImageNet pre-trained) | 2019-08-15 |
| Semi-supervised semantic segmentation needs strong, varied perturbations | ✓ Link | 66.48% | CutMix (DeepLab v2 ImageNet pre-trained) | 2019-06-05 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 62.9% | s4GAN+MLMT (DeepLab v2 ImageNet pre-trained) | 2019-08-15 |
| Adversarial Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 59.1% | Adversarial (DeepLab v2 ImageNet pre-trained) | 2018-02-22 |