Metric: Validation mIoU (higher is better)
| # | Model↕ | Validation mIoU▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | UniMatch V2 | 60.4 | No | UniMatch V2: Pushing the Limit of Semi-Supervise... | 2024-10-14 | Code |
| 2 | SemiVL | 55.4 | Yes | SemiVL: Semi-Supervised Semantic Segmentation wi... | 2023-11-27 | Code |
| 3 | AllSpark | 49.56 | No | AllSpark: Reborn Labeled Features from Unlabeled... | 2024-03-04 | Code |
| 4 | LogicDiag | 48.8 | No | Logic-induced Diagnostic Reasoning for Semi-supe... | 2023-08-24 | - |
| 5 | PrevMatch | 48.4 | No | Revisiting and Maximizing Temporal Knowledge in ... | 2024-05-31 | Code |
| 6 | UniMatch | 48.2 | No | Revisiting Weak-to-Strong Consistency in Semi-Su... | 2022-08-21 | Code |
| 7 | S4MC | 47.98 | No | Semi-Supervised Semantic Segmentation via Margin... | 2023-08-26 | Code |
| 8 | PC2Seg | 43.7 | No | Pixel Contrastive-Consistent Semi-Supervised Sem... | 2021-08-20 | - |
| 9 | PseudoSeg | 41.8 | No | PseudoSeg: Designing Pseudo Labels for Semantic ... | 2020-10-19 | Code |