# Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations

arXiv: https://arxiv.org/abs/2210.14670 · HTML: https://mlsanity.com/paper/2210.14670/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 48 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [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)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [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)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [Unsupervised Embedding Learning via Invariant and Spreading Instance Feature](https://mlsanity.com/paper/1904.03436/) (2019)
- [Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels](https://mlsanity.com/paper/2203.03884/) (2022)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank](https://mlsanity.com/paper/2104.13415/) (2021)
- [Guided Collaborative Training for Pixel-wise Semi-Supervised Learning](https://mlsanity.com/paper/2008.05258/) (2020)
- [Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2111.12903/) (2021)
- [Semi-supervised Semantic Segmentation with Directional Context-aware Consistency](https://mlsanity.com/paper/2106.14133/) (2021)
- [Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.09025/) (2021)
- [Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning](https://mlsanity.com/paper/2110.05474/) (2021)
- [SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.08808/) (2022)
- [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)
- [Deep Co-Training for Semi-Supervised Image Segmentation](https://mlsanity.com/paper/1903.11233/) (2019)

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

- [SimMatchV2: Semi-Supervised Learning with Graph Consistency](https://mlsanity.com/paper/2308.06692/) (2023)
- [Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2307.09755/) (2023)
- [PiClick: Picking the desired mask from multiple candidates in click-based interactive segmentation](https://mlsanity.com/paper/2304.11609/) (2023)
- [ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts](https://mlsanity.com/paper/2506.21835/) (2025)
- [Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2307.10097/) (2023)
- [CoNe: Contrast Your Neighbours for Supervised Image Classification](https://mlsanity.com/paper/2308.10761/) (2023)
- [Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localization](https://mlsanity.com/paper/2407.07673/) (2024)
- [Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2505.23438/) (2025)
- [Exploiting Minority Pseudo-Labels for Semi-Supervised Fine-grained Road Scene Understanding](https://mlsanity.com/paper/2409.12680/) (2024)
- [Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrast](https://mlsanity.com/paper/2409.18543/) (2024)

## Abstract (arXiv)

Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space. However, there exist inaccurate pseudo-labels which map the ambiguous representations of pixels to the wrong classes due to the limited cognitive ability of the model. In this paper, we define pixel-wise representations from a new perspective of probability theory and propose a Probabilistic Representation Contrastive Learning (PRCL) framework that improves representation quality by taking its probability into consideration. Through modelling the mapping from pixels to representations as the probability via multivariate Gaussian distributions, we can tune the contribution of the ambiguous representations to tolerate the risk of inaccurate pseudo-labels. Furthermore, we define prototypes in the form of distributions, which indicates the confidence of a class, while the point prototype cannot. Moreover, we propose to regularize the distribution variance to enhance the reliability of representations. Taking advantage of these benefits, high-quality feature representations can be derived in the latent space, thereby the performance of semantic segmentation can be further improved. We conduct sufficient experiment to evaluate PRCL on Pascal VOC and CityScapes to demonstrate its superiority. The code is available at https://github.com/Haoyu-Xie/PRCL.