Clustering-inspired Channel Selection Method for Weakly Supervised Object Localization

Xiaofeng Wang*, Zhe Liu, Xiangru Qiao, Zhiquan Li, Sidong Wu, Jiao Zhang, YONGHUAI LIU, Zhan Li, Hongbo Guo, HUAIZHONG ZHANG

*Corresponding author for this work

Research output: Contribution to journalArticle (journal)peer-review

Abstract

Weakly Supervised Object Localization (WSOL) aims to utilize the features learned by a classifier on the image-level labels to locate target objects. However, these existing channel selection methods for WSOL still cannot effectively select the important channels and remove the unimportant ones. To address this issue, we propose a Clustering-inspired Channel Selection method based on Class Activation Maps (CCS-CAM). Compared with the traditional methods, the advantage of CCS-CAM is that it is very simple yet effective for channel selection due to the K-means clustering based on Class Activation Maps. It can effectively ensure both object localization and classification accuracy. The effectiveness of the proposed CCS-CAM method has been demonstrated using multiple public datasets, with GT-Know Loc reaching 87.9% and 63.71% on the CUB200-2011 and ImageNet-1k respectively, which is superior to the other state-of-the-art methods.

Original languageEnglish
Pages (from-to)46-52
Number of pages7
JournalPattern Recognition Letters
Volume182
Issue number2024
Early online date12 Apr 2024
DOIs
Publication statusE-pub ahead of print - 12 Apr 2024

Keywords

  • Weakly Supervised Object Localization (WSOL)
  • Clustering-inspired Channel Selection
  • Class Activation Maps
  • Image Classification

Research Centres

  • Centre for Intelligent Visual Computing Research
  • Data and Complex Systems Research Centre

Fingerprint

Dive into the research topics of 'Clustering-inspired Channel Selection Method for Weakly Supervised Object Localization'. Together they form a unique fingerprint.

Cite this