UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation | ✓ Link | 83.6 | UniMatch V2 (DINOv2-B) | 2024-10-14 |
SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance | ✓ Link | 77.9 | SemiVL (ViT-B/16) | 2023-11-27 |
Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation | ✓ Link | 77.7% | PrevMatch (ResNet-101) | 2024-05-31 |
CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation | ✓ Link | 77.3 | CorrMatch (Deeplabv3+ with ResNet-101) | 2023-06-07 |
FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 77.2 | FARCLUSS | 2025-06-11 |
Semi-Supervised Semantic Segmentation via Marginal Contextual Information | ✓ Link | 77.00 | S4MC | 2023-08-26 |
Switching Temporary Teachers for Semi-Supervised Semantic Segmentation | ✓ Link | 76.81 | Dual Teacher (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2023-09-21 |
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation | ✓ Link | 76.59 | UniMatch (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2022-08-21 |
n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation | | 76.08 | n-CPS (ResNet-50) | 2021-12-14 |
Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning | ✓ Link | 75.83% | AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2021-10-11 |
Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation | ✓ Link | 75.8% | PrevMatch (ResNet-50) | 2024-05-31 |
Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation | ✓ Link | 75.00 | CW-BASS (DeepLab v3+ with ResNet-50) | 2025-02-21 |
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels | ✓ Link | 74.90% | U2PL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K, AEL) | 2022-03-08 |
Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization | ✓ Link | 73.41% | PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 2022-10-10 |
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | ✓ Link | 71.1% | Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) | 2022-10-18 |
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | ✓ Link | 70.65% | Dense FixMatch (DeepLabv3+ ResNet-50, uniform sampling, single pass eval) | 2022-10-18 |
Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation | ✓ Link | 69.92% | CPCL (DeepLab v3+ with ResNet-50) | 2022-11-30 |
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision | ✓ Link | 69.8 | CPS (DeepLab v3+ with ResNet-101) | 2021-06-02 |