| UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation | ✓ Link | 85.1% | UniMatch V2 (DINOv2-B) | 2024-10-14 |
| FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 81.0 | FARCLUSS | 2025-06-11 |
| SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance | ✓ Link | 80.6% | SemiVL (ViT-B/16) | 2023-11-27 |
| Switching Temporary Teachers for Semi-Supervised Semantic Segmentation | ✓ Link | 80.52 | Dual Teacher | 2023-09-21 |
| CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation | ✓ Link | 80.4% | CorrMatch (Deeplabv3+ with ResNet-101) | 2023-06-07 |
| Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning | ✓ Link | 80.28% | AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2021-10-11 |
| Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision | ✓ Link | 80.21% | CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) | 2021-06-02 |
| Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation | ✓ Link | 80.1% | PrevMatch (ResNet-101) | 2024-05-31 |
| Semi-Supervised Semantic Segmentation via Marginal Contextual Information | ✓ Link | 79.76% | S4MC | 2023-08-26 |
| Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation | ✓ Link | 79.5% | UniMatch | 2022-08-21 |
| n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation | | 79.29% | n-CPS (ResNet-50) | 2021-12-14 |
| Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation | ✓ Link | 79.22% | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference) | 2021-11-25 |
| Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation | ✓ Link | 79.2% | PrevMatch (ResNet-50) | 2024-05-31 |
| Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels | ✓ Link | 79.12% | U2PL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K, AEL) | 2022-03-08 |
| Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization | ✓ Link | 79.11% | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2022-10-10 |
| LaserMix for Semi-Supervised LiDAR Semantic Segmentation | ✓ Link | 79.1% | LaserMix (DeepLab v3+, ImageNet pre- trained ResNet50, single scale inference) | 2022-06-30 |
| A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation | ✓ Link | 78.7% | SimpleBaseline(DeepLabv3+ with ImageNet pretrained Xception65, single scale inference) | 2021-04-15 |
| Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation | ✓ Link | 78.17% | CPCL (DeepLab v3+ with ResNet-50) | 2022-11-30 |
| Semi-supervised Semantic Segmentation with Error Localization Network | ✓ Link | 75.33% | Error Localization Network (DeeplabV3 with ResNet-50) | 2022-04-05 |
| GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference | ✓ Link | 69.8% | GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained) | 2021-06-29 |
| Bootstrapping Semantic Segmentation with Regional Contrast | ✓ Link | 68.69% | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | 2021-04-09 |
| ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning | ✓ Link | 66.29% | ClassMix (DeepLab v2 MSCOCO pretrained) | 2020-07-15 |
| Adversarial Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 65.70% | Adversarial (DeepLab v2 ImageNet pre-trained) | 2018-02-22 |