| AllSpark | 80.92 | AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation | |
| PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 80.78 | Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization | |
| Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) | 72.04 | Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | |
| n-CPS (ResNet-50) | 75.85 | n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation | - |
| GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | 75.5% | GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference | |
| CW-BASS (DeepLab v3+ with ResNet-50) | 76.2 | Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation | - |
| CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) | 77.68% | Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision | |
| Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) | 69.02 | Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | |
| CPCL (DeepLab v3+ with ResNet-50) | 74.58 | Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation | |
| CPCL (DeepLab v3+ with ResNet-101) | 77.16 | Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation | |
| U2PL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K, CutMix) | 79.3 | Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels | |
| PCT (DeepLab v3+ with ResNet-50 pretrained on ImageNet-1K) | 76.47 | Learning Pseudo Labels for Semi-and-Weakly Supervised Semantic Segmentation | |
| n-CPS (ResNet-101) | 78.97 | n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation | - |
| ClassMix (DeepLab v2 MSCOCO pretrained) | 72.45 | ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning | |
| GuidedMix-Net(DeepLab v2 with ResNet101, input-size: 512x512 with multi-scale and flip, ImageNet pretrained) | 77.8% | GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference | |
| Error Localization Network (DeeplabV3 with ResNet-50) | 74.63% | Semi-supervised Semantic Segmentation with Error Localization Network | |
| CorrMatch (Deeplabv3+ with ResNet-101) | 80.9 | CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation | |
| Error Localization Network (DeeplabV3 with ResNet-101) | 76.58% | Semi-supervised Semantic Segmentation with Error Localization Network | |
| S4MC | 79.85 | Semi-Supervised Semantic Segmentation via Marginal Contextual Information | |
| Dual Teacher | 81.03 | Switching Temporary Teachers for Semi-Supervised Semantic Segmentation | |