Clustering-inspired channel selection method for weakly supervised object localization

doi:10.1016/j.patrec.2024.04.005

Clustering-inspired channel selection method for weakly supervised object localization

2024-06-01

0

PRE

AI

DOI：10.1016/j.patrec.2024.04.005

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Class activation map

Weakly supervised object localization

Image classification

Channel selection

Clustering

Clustering-inspired channel selection method for weakly supervised object localization

Abstract

Journal

Organization