Papers › Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation

Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation

30 Nov 2022arXiv:2211.16701archive 2025-07-28

Siqi Fan, Fenghua Zhu, Zunlei Feng, Yisheng Lv, Mingli Song, Fei-Yue Wang

Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo labels and leveraging all the pseudo labels. Addressing that, we propose a novel learning approach, called Conservative-Progressive Collaborative Learning (CPCL), among which two predictive networks are trained in parallel, and the pseudo supervision is implemented based on both the agreement and disagreement of the two predictions. One network seeks common ground via intersection supervision and is supervised by the high-quality labels to ensure a more reliable supervision, while the other network reserves differences via union supervision and is supervised by all the pseudo labels to keep exploring with curiosity. Thus, the collaboration of conservative evolution and progressive exploration can be achieved. To reduce the influences of the suspicious pseudo labels, the loss is dynamic re-weighted according to the prediction confidence. Extensive experiments demonstrate that CPCL achieves state-of-the-art performance for semi-supervised semantic segmentation.

PaperPDFCode

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

Code

leofansq/CPCL officialmentioned in paperpytorch 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

SegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 74.6% #18 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 76.98% #19 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 78.17% #18 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 69.92% #17 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 183 labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 67.02 #16 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled CPCL (DeepLab v3+ with ResNet-101) Validation mIoU 77.16 #17 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 74.58 #24 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 366 labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 72.14 #14 of 15 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 50% CPCL (DeepLab v3+ with ResNet-101) Validation mIoU 77.67% #8 of 14 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 50% CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 75.3% #12 of 14 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 732 labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 74.25 #16 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 92 labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 61.88 #17 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled CPCL (DeepLab v3+ with ResNet-101) Validation mIoU 76.4% #17 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 73.74% #23 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled CPCL (DeepLab v3+ with ResNet-101) Validation mIoU 73.44 #14 of 19 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled CPCL (DeepLab v3+ with ResNet-50) Validation mIoU 71.66 #16 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.

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