| Bootstrapping Semantic Segmentation with Regional Contrast | ✓ Link | 72.14% | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained) | 2021-04-09 |
| Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank | ✓ Link | 67.9% | SemiSegContrast
(DeepLab v2 with ResNet-101 backbone, MSCOCO pretrained) | 2021-04-27 |
| The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation | | 67.21% | GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained) | 2021-03-31 |
| DMT: Dynamic Mutual Training for Semi-Supervised Learning | ✓ Link | 67.15% | DMT (DeepLab v2 MSCOCO pre-trained) | 2020-04-18 |
| Semi-supervised semantic segmentation needs strong, varied perturbations | ✓ Link | 67.05% | CutMix (DeepLab v3+ ImageNet pre-trained) | 2019-06-05 |
| Bootstrapping Semantic Segmentation with Regional Contrast | ✓ Link | 66.41% | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | 2021-04-09 |
| ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning | ✓ Link | 66.15% | ClassMix (DeepLab v2 MSCOCO pretrained) | 2020-07-15 |
| Semi-supervised semantic segmentation needs strong, varied perturbations | ✓ Link | 64.81% | CutMix (DeepLab v2 ImageNet pre-trained) | 2019-06-05 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 63.3% | s4GAN + MLMT (DeepLab v2 MSCOCO/ImageNet pre-trained) | 2019-08-15 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 62.6% | s4GAN+MLMT (DeepLab v3+ ImageNet pre-trained) | 2019-08-15 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 60.4% | s4GAN+MLMT (DeepLab v2 ImageNet pre-trained) | 2019-08-15 |
| Adversarial Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 49.2% | Adversarial (DeepLab v2 ImageNet pre-trained) | 2018-02-22 |