EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Selective Multiple Classifiers for Weakly Supervised Semantic Segmentation

Zilin Guo, Dongyue Wu, Changxin Gao, Nong Sang

CAAI Transactions on Intelligence Technology · 2025-12 · 10 (6) · 1688-1702

DOI: 10.1049/cit2.70042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 24.08.2025. Verfasst von Zilin Guo und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing weakly supervised semantic segmentation (WSSS) methods based on image‐level labels always rely on class activation maps (CAMs), which measure the relationships between features and classifiers. However, CAMs only focus on the most discriminative regions of images, resulting in their poor coverage performance. We attribute this to the deficiency in the recognition ability of a single classifier and the negative impacts caused by magnitudes during the CAMs normalisation process. To address the aforementioned issues, we propose to construct selective multiple classifiers (SMC). During the training process, we extract multiple prototypes for each class and store them in the corresponding memory bank. These prototypes are divided into foreground and background prototypes, with the former used to identify foreground objects and the latter aimed at preventing the false activation of background pixels. As for the inference stage, multiple prototypes are adaptively selected from the memory bank for each image as SMC. Subsequently, CAMs are generated by measuring the angle between SMC and features. We enhance the recognition ability of classifiers by adaptively constructing multiple classifiers for each image, while only relying on angle measurement to generate CAMs can alleviate the suppression phenomenon caused by magnitudes. Furthermore, SMC can be integrated into other WSSS approaches to help generate better CAMs. Extensive experiments conducted on standard WSSS benchmarks such as PASCAL VOC 2012 and MS COCO 2014 demonstrate the superiority of our proposed method.

Förderung

  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China

Zitieren

APA

Guo, Z., Wu, D., Gao, C., & Sang, N. (2025). Selective Multiple Classifiers for Weakly Supervised Semantic Segmentation. CAAI Transactions on Intelligence Technology, 10(6), 1688-1702. https://doi.org/10.1049/cit2.70042

Vancouver

Guo Z, Wu D, Gao C, Sang N. Selective Multiple Classifiers for Weakly Supervised Semantic Segmentation. CAAI Transactions on Intelligence Technology. 2025;10(6):1688-1702. doi:10.1049/cit2.70042

BibTeX
@article{Guo2025,
  author = {Guo, Zilin and Wu, Dongyue and Gao, Changxin and Sang, Nong},
  title = {Selective Multiple Classifiers for Weakly Supervised Semantic Segmentation},
  journal = {CAAI Transactions on Intelligence Technology},
  year = {2025},
  volume = {10},
  number = {6},
  pages = {1688--1702},
  doi = {10.1049/cit2.70042}
}
Kostenlos starten →