TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/n-CPS: Generalising Cross Pseudo Supervision to n Networks...

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

Dominik Filipiak, Piotr Tempczyk, Marek Cygan

2021-12-14Semi-Supervised Semantic SegmentationSemantic Segmentation
PaperPDF

Abstract

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).

Results

TaskDatasetMetricValueModel
Semantic SegmentationPascal VOC 2012 6.25% labeledValidation mIoU75.86n-CPS (ResNet-101)
Semantic SegmentationPascal VOC 2012 6.25% labeledValidation mIoU72.03n-CPS (ResNet-50)
Semantic SegmentationPASCAL VOC 2012 25% labeledValidation mIoU78.97n-CPS (ResNet-101)
Semantic SegmentationPASCAL VOC 2012 25% labeledValidation mIoU75.85n-CPS (ResNet-50)
Semantic SegmentationCityscapes 6.25% labeledValidation mIoU76.08n-CPS (ResNet-50)
10-shot image generationPascal VOC 2012 6.25% labeledValidation mIoU75.86n-CPS (ResNet-101)
10-shot image generationPascal VOC 2012 6.25% labeledValidation mIoU72.03n-CPS (ResNet-50)
10-shot image generationPASCAL VOC 2012 25% labeledValidation mIoU78.97n-CPS (ResNet-101)
10-shot image generationPASCAL VOC 2012 25% labeledValidation mIoU75.85n-CPS (ResNet-50)
10-shot image generationCityscapes 6.25% labeledValidation mIoU76.08n-CPS (ResNet-50)

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17SAMST: A Transformer framework based on SAM pseudo label filtering for remote sensing semi-supervised semantic segmentation2025-07-16Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping2025-07-15U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV2025-07-15