Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching

Dingwen Zhang, Hao Li, Wenyuan Zeng, Chaowei Fang, Lechao Cheng, Ming Ming Cheng, Junwei Han

科研成果: 期刊稿件文章同行评审

35 引用 (Scopus)

摘要

Weakly supervised semantic segmentation (WSSS) is a challenging yet important research field in vision community. In WSSS, the key problem is to generate high-quality pseudo segmentation masks (PSMs). Existing approaches mainly depend on the discriminative object part to generate PSMs, which would inevitably miss object parts or involve surrounding image background, as the learning process is unaware of the full object structure. In fact, both the discriminative object part and the full object structure are critical for deriving of high-quality PSMs. To fully explore these two information cues, we build a novel end-to-end learning framework, alternate self-dual teaching (ASDT), based on a dual-teacher single-student network architecture. The information interaction among different network branches is formulated in the form of knowledge distillation (KD). Unlike the conventional KD, the knowledge of the two teacher models would inevitably be noisy under weak supervision. Inspired by the Pulse Width (PW) modulation, we introduce a PW wave-like selection signal to alleviate the influence of the imperfect knowledge from either teacher model on the KD process. Comprehensive experiments on the PASCAL VOC 2012 and COCO-Stuff 10K demonstrate the effectiveness of the proposed ASDT framework, and new state-of-the-art results are achieved.

源语言英语
页(从-至)3086-3095
页数10
期刊IEEE Transactions on Image Processing
34
DOI
出版状态已出版 - 2025

指纹

探究 'Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching' 的科研主题。它们共同构成独一无二的指纹。

引用此