Towards Prior Gap and Representation Gap for Long-tailed Recognition, Pattern Recognition
Zhang Ming-Liang1,2; Zhang Xu-Yao1,2; Wang Chang1,2; Liu Cheng-Lin1,2
发表期刊Pattern Recognition
ISSN0031-3203
2023-01
卷号133期号:109012页码:109012
文章类型模式识别,机器学习
摘要

Most deep learning models are elaborately designed for balanced datasets, and thus they inevitably suffer performance degradation in practical long-tailed recognition tasks, especially to the minority classes. There are two crucial issues in learning from imbalanced datasets: skew decision boundary and unrepresentative feature space. In this work, we establish a theoretical framework to analyze the sources of these two issues from Bayesian perspective, and find that they are closely related to the prior gap and the representation gap, respectively. Under this framework, we show that existing long-tailed recognition methods manage to remove either the prior gap or the presentation gap. Different from these methods, we propose to simultaneously remove the two gaps to achieve more accurate long-tailed recognition. Specifically, we propose the prior calibration strategy to remove the prior gap and introduce three strategies (representative feature extraction, optimization strategy adjustment and effective sample modeling) to mitigate the representation gap. Extensive experiments on five benchmark datasets validate the superiority of our method against the state-of-the-art competitors.

关键词Long-tailed learning Prior gap Representation gap Image recognition
DOI10.1016/j.patcog.2022.109012
收录类别SCI
语种英语
是否为代表性论文
七大方向——子方向分类模式识别基础
国重实验室规划方向分类其他
是否有论文关联数据集需要存交
引用统计
被引频次:7[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/55699
专题多模态人工智能系统全国重点实验室
通讯作者Zhang Ming-Liang
作者单位1.National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Zhang Ming-Liang,Zhang Xu-Yao,Wang Chang,et al. Towards Prior Gap and Representation Gap for Long-tailed Recognition, Pattern Recognition[J]. Pattern Recognition,2023,133(109012):109012.
APA Zhang Ming-Liang,Zhang Xu-Yao,Wang Chang,&Liu Cheng-Lin.(2023).Towards Prior Gap and Representation Gap for Long-tailed Recognition, Pattern Recognition.Pattern Recognition,133(109012),109012.
MLA Zhang Ming-Liang,et al."Towards Prior Gap and Representation Gap for Long-tailed Recognition, Pattern Recognition".Pattern Recognition 133.109012(2023):109012.
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
1-s2.0-S003132032200(2258KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang Ming-Liang]的文章
[Zhang Xu-Yao]的文章
[Wang Chang]的文章
百度学术
百度学术中相似的文章
[Zhang Ming-Liang]的文章
[Zhang Xu-Yao]的文章
[Wang Chang]的文章
必应学术
必应学术中相似的文章
[Zhang Ming-Liang]的文章
[Zhang Xu-Yao]的文章
[Wang Chang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 1-s2.0-S0031320322004927-main.pdf
格式: Adobe PDF
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。