Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation

arXiv:2404.08195v1 Announce Type: new
Abstract: Weakly supervised semantic segmentation (WSSS) with image-level labels intends to achieve dense tasks without laborious annotations. However, due to the ambiguous contexts and fuzzy regions, the performance of WSSS, especially the stages of generating Class Activation Maps (CAMs) and refining pseudo masks, widely suffers from ambiguity while being barely noticed by previous literature. In this work, we propose UniA, a unified single-staged WSSS framework, to efficiently tackle this issue from the perspective of uncertainty inference …

abstract annotations arxiv class cs.cv diversification however image inference labels maps performance perspective segmentation semantic tasks type uncertainty