.png){kind=icon}
返回
PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-024-02016-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Semi-supervised semantic segmentation
Contrastive learning
Probabilistic representation
Robust learning
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
DMT: Dynamic mutual training for semi-supervised learningDMT: 半监督学习的动态互训练.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Simultaneous confidence interval estimation for successive comparisons of ordered treatment effects
PREAI
分享收藏
查看更多内容