| Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model | ✓ Link | 82.4 | SemiOVS (w/ UniMatch, ResNet-101) | 2025-07-04 |
| Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model | ✓ Link | 82.3 | SemiOVS (w/ PrevMatch, ResNet-101) | 2025-07-04 |
| AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation | ✓ Link | 82.04% | AllSpark | 2024-03-04 |
| Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation | ✓ Link | 81.92% | UniMatch | 2022-08-21 |
| Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation | ✓ Link | 81.9 | PrevMatch (ResNet-101) | 2024-05-31 |
| CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation | ✓ Link | 81.9% | CorrMatch (Deeplabv3+ with ResNet-101) | 2023-06-07 |
| Switching Temporary Teachers for Semi-Supervised Semantic Segmentation | ✓ Link | 81.19 | Dual Teacher | 2023-09-21 |
| Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization | ✓ Link | 80.71% | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2022-10-10 |
| Semi-Supervised Semantic Segmentation via Marginal Contextual Information | ✓ Link | 79.67% | S4MC | 2023-08-26 |
| Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels | ✓ Link | 79.01% | U2PL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K, CutMix) | 2022-03-08 |
| Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation | ✓ Link | 78.20% | PS-MT | 2021-11-25 |
| FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 78.2 | FARCLUSS | 2025-06-11 |
| n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation | | 77.99% | n-CPS (ResNet-101) | 2021-12-14 |
| Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning | ✓ Link | 77.57% | AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2021-10-11 |
| Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision | ✓ Link | 76.44% | CPS | 2021-06-02 |
| GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference | ✓ Link | 76.4% | GuidedMix-Net | 2021-06-29 |
| Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation | ✓ Link | 76.4% | CPCL (DeepLab v3+ with ResNet-101) | 2022-11-30 |
| Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 75.81% | CW-BASS (DeepLab v3+ with ResNet-50) | 2025-02-21 |
| Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation | ✓ Link | 75.70% | PS-MT | 2021-11-25 |
| Learning Pseudo Labels for Semi-and-Weakly Supervised Semantic Segmentation | ✓ Link | 75.52% | PCT (DeepLab v3+ with ResNet-50 pretrained on ImageNet-1K) | 2022-08-02 |
| Semi-supervised Semantic Segmentation with Error Localization Network | ✓ Link | 75.10% | Error Localization Network | 2022-04-05 |
| n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation | | 74.21% | n-CPS | 2021-12-14 |
| Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation | ✓ Link | 73.74% | CPCL (DeepLab v3+ with ResNet-50) | 2022-11-30 |
| GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference | ✓ Link | 73.4% | GuidedMix-Net | 2021-06-29 |
| Semi-supervised Semantic Segmentation with Error Localization Network | ✓ Link | 73.2% | Error Localization Network | 2022-04-05 |
| DMT: Dynamic Mutual Training for Semi-Supervised Learning | ✓ Link | 72.70% | DMT | 2020-04-18 |
| Semi-supervised semantic segmentation needs strong, varied perturbations | ✓ Link | 72.45% | CutMix | 2019-06-05 |
| Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank | ✓ Link | 71.6% | SemiSegContrast | 2021-04-27 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 71.4% | s4GAN + MLMT | 2019-08-15 |
| ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning | ✓ Link | 71.00% | ClassMix | 2020-07-15 |
| Bootstrapping Semantic Segmentation with Regional Contrast | ✓ Link | 71.00% | ReCo | 2021-04-09 |
| The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation | | 70.76% | GIST and RIST | 2021-03-31 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 70.4% | s4GAN+MLMT | 2019-08-15 |
| Semi-supervised semantic segmentation needs strong, varied perturbations | ✓ Link | 67.6% | CutMix | 2019-06-05 |
| Semi-Supervised Semantic Segmentation with High- and Low-level Consistency | ✓ Link | 67.3% | s4GAN+MLMT | 2019-08-15 |
| Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | ✓ Link | 65.82% | Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) | 2022-10-18 |
| Adversarial Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 64.3% | Adversarial | 2018-02-22 |
| Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | ✓ Link | 62.49% | Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) | 2022-10-18 |