Abstract
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained attention for its cost-effectiveness. Most existing methods emphasize inter-class separation, often neglecting the shared semantics among related categories and lacking fine-grained discrimination. To address this, we propose Contrastive Prompt Clustering (CPC), a novel WSSS framework. CPC exploits Large Language Models (LLMs) to derive category clusters that encode intrinsic inter-class relationships, and further introduces a class-aware patch-level contrastive loss to enforce intra-class consistency and inter-class separation. This hierarchical design leverages clusters as coarse-grained semantic priors while preserving fine-grained boundaries, thereby reducing confusion among visually similar categories. Experiments on PASCAL VOC 2012 and MS COCO 2014 demonstrate that CPC surpasses existing state-of-the-art methods in WSSS.
Abstract (translated)
弱监督语义分割（WSSS）使用图像级标签已经因其成本效益而受到关注。大多数现有的方法侧重于类间分离，往往忽略了相关类别之间的共享语义，并且缺乏细粒度的区分能力。为了解决这些问题，我们提出了对比提示聚类（Contrastive Prompt Clustering, CPC），这是一种新颖的WSSS框架。CPC利用大型语言模型（LLMs）来推导编码固有类间关系的类别簇，并进一步引入了一种以类别为中心的patch级对比损失，用以强化类内一致性并保持类间分离。这种分层设计利用簇作为粗粒度语义先验的同时保留细粒度边界，从而减少视觉上相似类别之间的混淆。在PASCAL VOC 2012和MS COCO 2014数据集上的实验表明，CPC超越了现有的WSSS方法的最先进水平。
URL
https://arxiv.org/abs/2508.17009
