PRCL：用于半监督语义分割的概率表示对比学习
PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation
AI总结：
针对半监督语义分割中自指导噪声干扰无监督训练的问题，提出 PRCL 框架，利用概率表示、全局分布原型和虚拟负样本增强对比学习鲁棒性，并在两个基准上验证优越性。
摘要：
通过对比学习，半监督语义分割（S4）已经取得了巨大突破。然而，由于标注有限，针对无标注图像的指导由模型自身生成，这不可避免地存在噪声，并干扰无监督训练过程。为解决这一问题，我们提出了一种鲁棒的基于对比的 S4 框架，称为概率表示对比学习（Probabilistic Representation Contrastive Learning，PRCL）框架，以增强无监督训练过程的鲁棒性。我们通过多元高斯分布将像素级表示建模为概率表示（Probabilistic Representations，PR），并调整模糊表示的贡献，以容忍对比学习中不准确指导的风险。此外，我们通过在整个训练过程中收集所有 PR 来引入全局分布原型（Global Distribution Prototypes，GDP）。由于 GDP 包含同一类别所有表示的信息，因此它不受表示中瞬时噪声的影响，并能承受表示的类内方差。另外，我们基于 GDP 生成虚拟负样本（Virtual Negatives，VNs），使其参与对比学习过程。在两个公开基准上进行的大量实验证明了我们 PRCL 框架的优越性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
