Comprehensive Feature Processing Based on Attention Mechanism for Co-Salient Object Detection
Guohua Lv, Mao Yuan, Zengbin Zhang, Zhengyang Zhang, Zhenhui Ding, Guangxiao Ma
Abstract
Co-salient object detection (CoSOD) aims to detect common salient objects across multiple related images. However, existing methods often struggle with limited attention coverage, missing some co-salient objects. To address this, we propose a two-stage feature processing module (FPM) comprising comprehensive feature extraction module (CFE) and feature enhancement module (FEM). CFE extracts comprehensive cosalient features while reducing background noise, and FEM enhances feature representation and adjusts attention weights for full object coverage. Additionally, we introduce an adversarial learning module (ALM) to improve prediction quality by reducing noise in the co-salient regions. Extensive experiments on three benchmark datasets—CoCA, CoSOD3k, and CoSal2015—demonstrate that our model significantly outperforms state-of-the-art methods. The source code is available at https://github.com/yaobaimiao/CFPAM.
BibTeX
@inproceedings{icassp2025_comprehensivefea,
title = {Comprehensive Feature Processing Based on Attention Mechanism for Co-Salient Object Detection},
author = {Guohua Lv and Mao Yuan and Zengbin Zhang and Zhengyang Zhang and Zhenhui Ding and Guangxiao Ma},
booktitle = {ICASSP 2025},
year = {2025}
}