Papers › Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

10 Oct 2022arXiv:2210.04388archive 2025-07-28

Hai-Ming Xu, Lingqiao Liu, Qiuchen Bian, Zhen Yang

Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation, i.e., regions belonging to the same class may exhibit a very different appearance even in the same picture. This diversity will make the label propagation hard from pixels to pixels. To address this problem, we propose a novel approach to regularize the distribution of within-class features to ease label propagation difficulty. Specifically, our approach encourages the consistency between the prediction from a linear predictor and the output from a prototype-based predictor, which implicitly encourages features from the same pseudo-class to be close to at least one within-class prototype while staying far from the other between-class prototypes. By further incorporating CutMix operations and a carefully-designed prototype maintenance strategy, we create a semi-supervised semantic segmentation algorithm that demonstrates superior performance over the state-of-the-art methods from extensive experimental evaluation on both Pascal VOC and Cityscapes benchmarks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

heimingx/semi_seg_proto officialmentioned in papermindspore report

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

DiversitySemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 76.31% #17 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 78.4% #15 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 79.11% #15 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 73.41% #14 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 80.78 #7 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 50% PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 80.91% #2 of 14 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 80.71% #8 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K) Validation mIoU 78.6 #9 of 19 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.

Methods

CutMix

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