Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentation
This work addresses the challenge of fine-grained discrimination in weakly supervised semantic segmentation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of weakly supervised semantic segmentation with image-level labels by proposing Contrastive Prompt Clustering (CPC), which uses LLMs to create category clusters and a contrastive loss for better discrimination, achieving state-of-the-art results on PASCAL VOC 2012 and MS COCO 2014 datasets.
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.