Context Patch Fusion With Class Token Enhancement for Weakly Supervised Semantic Segmentation
This work addresses segmentation accuracy issues in WSSS for computer vision applications, representing an incremental advancement by integrating spatial and semantic cues more effectively.
The paper tackles the problem of incomplete local representations and limited segmentation accuracy in Weakly Supervised Semantic Segmentation (WSSS) by proposing the CPF-CTE framework, which exploits contextual dependencies among patches and uses learnable class tokens, resulting in consistent improvements over prior methods on PASCAL VOC 2012 and MS COCO 2014 datasets.
Weakly Supervised Semantic Segmentation (WSSS), which relies only on image-level labels, has attracted significant attention for its cost-effectiveness and scalability. Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations. However, they often neglect the complex contextual dependencies among image patches, resulting in incomplete local representations and limited segmentation accuracy. To address these issues, we propose the Context Patch Fusion with Class Token Enhancement (CPF-CTE) framework, which exploits contextual relations among patches to enrich feature representations and improve segmentation. At its core, the Contextual-Fusion Bidirectional Long Short-Term Memory (CF-BiLSTM) module captures spatial dependencies between patches and enables bidirectional information flow, yielding a more comprehensive understanding of spatial correlations. This strengthens feature learning and segmentation robustness. Moreover, we introduce learnable class tokens that dynamically encode and refine class-specific semantics, enhancing discriminative capability. By effectively integrating spatial and semantic cues, CPF-CTE produces richer and more accurate representations of image content. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate that CPF-CTE consistently surpasses prior WSSS methods.