Papers › Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
Yuyuan Liu, Yu Tian, Yuanhong Chen, Fengbei Liu, Vasileios Belagiannis, Gustavo Carneiro
Consistency learning using input image, feature, or network perturbations has shown remarkable results in semi-supervised semantic segmentation, but this approach can be seriously affected by inaccurate predictions of unlabelled training images. There are two consequences of these inaccurate predictions: 1) the training based on the "strict" cross-entropy (CE) loss can easily overfit prediction mistakes, leading to confirmation bias; and 2) the perturbations applied to these inaccurate predictions will use potentially erroneous predictions as training signals, degrading consistency learning. In this paper, we address the prediction accuracy problem of consistency learning methods with novel extensions of the mean-teacher (MT) model, which include a new auxiliary teacher, and the replacement of MT's mean square error (MSE) by a stricter confidence-weighted cross-entropy (Conf-CE) loss. The accurate prediction by this model allows us to use a challenging combination of network, input data and feature perturbations to improve the consistency learning generalisation, where the feature perturbations consist of a new adversarial perturbation. Results on public benchmarks show that our approach achieves remarkable improvements over the previous SOTA methods in the field. Our code is available at https://github.com/yyliu01/PS-MT.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Semantic Segmentation | Cityscapes 12.5% labeled | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet50, single scale inference) | Validation mIoU | 77.12% | #14 of 33 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 25% labeled | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference) | Validation mIoU | 78.38% | #16 of 30 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Cityscapes 50% labeled | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference) | Validation mIoU | 79.22% | #12 of 23 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 1464 labels | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) | Validation mIoU | 80.01 | #11 of 17 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 1464 labels | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference) | Validation mIoU | 78.08 | #14 of 17 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 25% labeled | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) | Validation mIoU | 78.72 | #13 of 27 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | PASCAL VOC 2012 50% | PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference) | Validation mIoU | 79.76% | #6 of 14 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Pascal VOC 2012 12.5% labeled | PS-MT | Validation mIoU | 78.20% | #11 of 38 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Pascal VOC 2012 12.5% labeled | PS-MT | Validation mIoU | 75.70% | #19 of 38 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections