| Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) | 65.82% | Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | |
| CW-BASS (DeepLab v3+ with ResNet-50) | 75.81% | Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation | - |
| U2PL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K, CutMix) | 79.01% | Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels | |
| PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 80.71% | Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization | |
| Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) | 62.49% | Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks | |
| AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) | 77.57% | Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning | |