English

PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation

Computer Vision and Pattern Recognition 2024-02-29 v1 Machine Learning

Abstract

Tremendous breakthroughs have been developed in Semi-Supervised Semantic Segmentation (S4) through contrastive learning. However, due to limited annotations, the guidance on unlabeled images is generated by the model itself, which inevitably exists noise and disturbs the unsupervised training process. To address this issue, we propose a robust contrastive-based S4 framework, termed the Probabilistic Representation Contrastive Learning (PRCL) framework to enhance the robustness of the unsupervised training process. We model the pixel-wise representation as Probabilistic Representations (PR) via multivariate Gaussian distribution and tune the contribution of the ambiguous representations to tolerate the risk of inaccurate guidance in contrastive learning. Furthermore, we introduce Global Distribution Prototypes (GDP) by gathering all PRs throughout the whole training process. Since the GDP contains the information of all representations with the same class, it is robust from the instant noise in representations and bears the intra-class variance of representations. In addition, we generate Virtual Negatives (VNs) based on GDP to involve the contrastive learning process. Extensive experiments on two public benchmarks demonstrate the superiority of our PRCL framework.

Keywords

Cite

@article{arxiv.2402.18117,
  title  = {PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation},
  author = {Haoyu Xie and Changqi Wang and Jian Zhao and Yang Liu and Jun Dan and Chong Fu and Baigui Sun},
  journal= {arXiv preprint arXiv:2402.18117},
  year   = {2024}
}

Comments

19 pages, 11 figures

R2 v1 2026-06-28T15:02:55.293Z