P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors

arXiv:2305.12522v3 Announce Type: replace-cross
Abstract: Weakly Supervised Semantic Segmentation (WSSS) techniques explore individual regularization strategies to refine Class Activation Maps (CAMs). In this work, we first analyze complementary WSSS techniques in the literature, their segmentation properties, and the conditions in which they are most effective. Based on these findings, we devise two new techniques: P-NOC and CCAM-H. In the first, we promote the conjoint training of two adversarial CAM generating networks: the generator, which progressively learns to erase regions containing …

abstract adversarial adversarial training analyze arxiv class cs.cv cs.lg explore literature maps networks refine regularization robust segmentation semantic strategies training type work