Papers › n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised...

n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation

14 Dec 2021arXiv:2112.07528archive 2025-07-28

Dominik Filipiak, Piotr Tempczyk, Marek Cygan

We present n-CPS - a generalisation of the recent state-of-the-art cross pseudo supervision (CPS) approach for the task of semi-supervised semantic segmentation. In n-CPS, there are n simultaneously trained subnetworks that learn from each other through one-hot encoding perturbation and consistency regularisation. We also show that ensembling techniques applied to subnetworks outputs can significantly improve the performance. To the best of our knowledge, n-CPS paired with CutMix outperforms CPS and sets the new state-of-the-art for Pascal VOC 2012 with (1/16, 1/8, 1/4, and 1/2 supervised regimes) and Cityscapes (1/16 supervised).

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled n-CPS (ResNet-50) Validation mIoU 77.61% #12 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled n-CPS (ResNet-50) Validation mIoU 78.41% #14 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled n-CPS (ResNet-50) Validation mIoU 79.29% #11 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled n-CPS (ResNet-50) Validation mIoU 76.08 #9 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled n-CPS (ResNet-101) Validation mIoU 78.97 #12 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled n-CPS (ResNet-50) Validation mIoU 75.85 #21 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 50% n-CPS (ResNet-101) Validation mIoU 80.26% #5 of 14 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 50% n-CPS (ResNet-50) Validation mIoU 77.07% #10 of 14 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled n-CPS (ResNet-101) Validation mIoU 77.99% #13 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled n-CPS Validation mIoU 74.21% #22 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled n-CPS (ResNet-101) Validation mIoU 75.86 #13 of 19 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled n-CPS (ResNet-50) Validation mIoU 72.03 #15 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