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

arXiv: https://arxiv.org/abs/2112.07528 · HTML: https://mlsanity.com/paper/2112.07528/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Guided Collaborative Training for Pixel-wise Semi-Supervised Learning](https://mlsanity.com/paper/2008.05258/) (2020)
- [Bootstrapping Semantic Segmentation with Regional Contrast](https://mlsanity.com/paper/2104.04465/) (2021)
- [DMT: Dynamic Mutual Training for Semi-Supervised Learning](https://mlsanity.com/paper/2004.08514/) (2020)

## Built on by (most cited first, 10 of 10)

- [Diverse Cotraining Makes Strong Semi-Supervised Segmentor](https://mlsanity.com/paper/2308.09281/) (2023)
- [Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students](https://mlsanity.com/paper/2209.02178/) (2022)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [SHREC 2022: pothole and crack detection in the road pavement using images and RGB-D data](https://mlsanity.com/paper/2205.13326/) (2022)
- [Progressive Learning with Cross-Window Consistency for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2211.12425/) (2022)
- [Confidence-Guided Semi-supervised Learning in Land Cover Classification](https://mlsanity.com/paper/2305.10344/) (2023)
- [Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning](https://mlsanity.com/paper/2402.05305/) (2024)
- [Integrating Semi-Supervised and Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2501.19227/) (2025)
- [DiverseNet: Decision Diversified Semi-supervised Semantic Segmentation Networks for Remote Sensing Imagery](https://mlsanity.com/paper/2311.13716/) (2023)
- [Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus](https://mlsanity.com/paper/2607.28304/) (2026)

## Abstract (arXiv)

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).