CASIA OpenIR  > 复杂系统认知与决策实验室  > 智能系统与工程
Feature Comparison Based Channel Attention For Fine-Grained Visual Classification
Shukun Jia; Yan Bai; Zhang Jing
Conference Name2020 IEEE International Conference on Image Processing (ICIP)
Conference Date25-28 October 2020
Conference PlaceAbu Dhabi, United Arab Emirates

Fine-grained visual classification (FGVC) remains challenging because a majority of samples have large intra-class variations and small inter-class variations. However, samples belonging to one category are essentially identical in some discriminative visual patterns. Intuitively, we want models to reinforce the relationship between these discriminative visual patterns and image-level labels. In this paper, we propose a feature comparison based channel attention (FCCA) to achieve this intuition. In FCCA, the feature comparison mechanism is designed to recognize discriminative visual patterns. The weights assignment scheme guarantees that feature channels related to discriminative visual patterns have larger weights. The state-of-the-art performance has been achieved on two public FGVC datasets. Extensive experiments further prove the effectiveness of our method.

Indexed ByEI
Sub direction classification图像视频处理与分析
planning direction of the national heavy laboratory视觉信息处理
Paper associated data
Document Type会议论文
AffiliationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Shukun Jia,Yan Bai,Zhang Jing. Feature Comparison Based Channel Attention For Fine-Grained Visual Classification[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
4.pdf(163KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shukun Jia]'s Articles
[Yan Bai]'s Articles
[Zhang Jing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shukun Jia]'s Articles
[Yan Bai]'s Articles
[Zhang Jing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shukun Jia]'s Articles
[Yan Bai]'s Articles
[Zhang Jing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 4.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.