Class Activation Map Calibration for Weakly Supervised Semantic Segmentation

Wang, Jian, Dai, Tianhong, Zhao, Xinqiao, Garcia-Fernandez, Angel F ORCID: 0000-0002-6471-8455, Lim, Eng Gee ORCID: 0000-0003-0199-7386 and Xiao, Jimin (2024) Class Activation Map Calibration for Weakly Supervised Semantic Segmentation IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 34 (11). pp. 11668-11681. ISSN 1051-8215, 1558-2205

Text Wang24_elements.pdf - Author Accepted Manuscript Available under License Creative Commons Attribution. Download (9MB) | Preview

Abstract

Image-level weakly supervised semantic segmentation (WSSS) has received substantial attention due to its cost-effective annotation process. In WSSS, Class Activation Maps (CAMs) generated via classifier weights tend to focus on the most discriminative region, while the CAMs derived from class prototypes are significantly enhanced to cover more complete regions. However, the prototype CAMs still exhibit limitations such as incomplete localization maps on target objects and the presence of background noise. In this paper, we propose a novel WSSS framework called Classifier-Prototype Mutual Calibration (CPMC) that leverages the characteristics of both classifier and prototype CAMs to address the above issues. Specifically, an iterative refinement strategy based on context feature dependency is applied to refine the original classifier CAMs, which helps to generate improved prototype CAMs. Subsequently, local prototypes are constructed based on the false negative regions and false positive regions extracted from the previous two CAMs, which contribute to completing missing parts of the target object and suppressing background noise respectively. Therefore, CPMC can alleviate the aforementioned issues. Extensive experimental results on standard WSSS benchmarks (PASCAL VOC and MS COCO) show that our method significantly improves the quality of CAMs and achieves state-of-the-art performance. Our source code will be released.

Item Type:	Article
Uncontrolled Keywords:	Weakly supervised, semantic segmentation, class activation maps calibration
Depositing User:	Symplectic Admin
Date Deposited:	29 Jul 2024 08:46
Last Modified:	23 May 2026 08:58
DOI:	10.1109/TCSVT.2024.3427720
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3183038
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.