Prototype calibration for long tailed recognition
2023-07-10
会议录名称2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)
ISSN1945-7871
卷号2023-July
页码2123-2128
发表状态已发表
DOI10.1109/ICME55011.2023.00363
摘要In the real world, data distribution usually presents imbalanced characteristics, such as long-tailed distribution, which is generally divided into the head and tail classes. For tail classes, image features cannot be represented well due to insufficient training samples. It is a vital task to learn discriminative image representation on imbalanced data distribution. In our work, through exploring prototype information, we propose a prototype-based contrastive learning(PCL) loss and prototype-based feature augmentation(PFA) module to improve the accuracy of the classifier on the imbalanced dataset. Specifically, we utilize the classifier parameters to generate learnable embeddings, which can be regarded as the class centers after using metric learning. The PFA module generates the image features of each tail class with the help of head class information. We validate our approach on common long-tailed benchmarks. Our results indicate that the PCL and PFA make the classification model achieve significant performance boosts on these benchmarks. © 2023 IEEE.
会议录编者/会议主办者et al. ; IEEE Circuits and Systems (CAS) ; IEEE Communications (ComSoc) ; IEEE Computer (CS) ; IEEE Signal Processing (SPS) ; Tencent
关键词Long tailed recognition Few-shot learning Prototype Network Contrastive Learning
会议名称2023 IEEE International Conference on Multimedia and Expo, ICME 2023
会议地点Brisbane, Australia
会议日期10-14 July 2023
URL查看原文
收录类别EI
语种英语
出版者IEEE Computer Society
EI入藏号20233814738670
EI主题词Image representation
EISSN1945-788X
EI分类号716.1 Information Theory and Signal Processing ; 723.4 Artificial Intelligence ; 723.5 Computer Applications ; 741.2 Vision ; 903.1 Information Sources and Analysis
原始文献类型Conference article (CA)
来源库IEEE
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/333423
专题创意与艺术学院_PI研究组(P)_武颖娜组
物质科学与技术学院_硕士生
信息科学与技术学院_硕士生
创意与艺术学院_PI研究组(P)_杨锐组
作者单位
ShanghaiTech University, Shanghai, China
第一作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Zhongan Wang,Shuai Shi,Yingna Wu,et al. Prototype calibration for long tailed recognition[C]//et al., IEEE Circuits and Systems (CAS), IEEE Communications (ComSoc), IEEE Computer (CS), IEEE Signal Processing (SPS), Tencent:IEEE Computer Society,2023:2123-2128.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Zhongan Wang]的文章
[Shuai Shi]的文章
[Yingna Wu]的文章
百度学术
百度学术中相似的文章
[Zhongan Wang]的文章
[Shuai Shi]的文章
[Yingna Wu]的文章
必应学术
必应学术中相似的文章
[Zhongan Wang]的文章
[Shuai Shi]的文章
[Yingna Wu]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。