Knowledge Commons of Institute of Automation,CAS
Feature Comparison Based Channel Attention For Fine-Grained Visual Classification | |
Shukun Jia; Yan Bai; Zhang Jing | |
2022 | |
会议名称 | 2020 IEEE International Conference on Image Processing (ICIP) |
会议日期 | 25-28 October 2020 |
会议地点 | Abu Dhabi, United Arab Emirates |
摘要 | 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. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57474 |
专题 | 复杂系统认知与决策实验室_智能系统与工程 |
作者单位 | Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Shukun Jia,Yan Bai,Zhang Jing. Feature Comparison Based Channel Attention For Fine-Grained Visual Classification[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
4.pdf(163KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论