Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
| Towards prior gap and representation gap for long-tailed recognition | |
Zhang, Ming-Liang1,2; Zhang, Xu-Yao1,2 ; Wang, Chuang1,2; Liu, Cheng-Lin1,2
| |
| Source Publication | PATTERN RECOGNITION
 |
| ISSN | 0031-3203 |
| 2023 | |
| Volume | 133Pages:12 |
| Corresponding Author | Zhang, Ming-Liang(zhangmingliang2018@ia.ac.cn) |
| Abstract | Most deep learning models are elaborately designed for balanced datasets, and thus they inevitably suf-fer 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 unrep-resentative 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 strate-gies (representative feature extraction, optimization strategy adjustment and effective sample modeling) to mitigate the representation gap. Extensive experiments on five benchmark datasets validate the supe-riority of our method against the state-of-the-art competitors.(c) 2022 Elsevier Ltd. All rights reserved. |
| Keyword | Long-tailed learning Prior gap Representation gap Image recognition |
| DOI | 10.1016/j.patcog.2022.109012 |
| WOS Keyword | NEURAL-NETWORK CLASSIFICATION |
| Indexed By | SCI |
| Language | 英语 |
| Funding Project | National Key Research and Development Program[2018AAA010 040 0] ; National Natural Science Foundation of China (NSFC)[U20A20223] ; National Natural Science Foundation of China (NSFC)[62076236] ; National Natural Science Foundation of China (NSFC)[61721004] |
| Funding Organization | National Key Research and Development Program ; National Natural Science Foundation of China (NSFC) |
| WOS Research Area | Computer Science ; Engineering |
| WOS Subject | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
| WOS ID | WOS:000863094500012 |
| Publisher | ELSEVIER SCI LTD |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/50309 |
| Collection | 模式识别国家重点实验室_模式分析与学习 |
| Corresponding Author | Zhang, Ming-Liang |
| Affiliation | 1.Chinese Acad Sci, Natl Lab Pattern Recognit NLPR, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| First Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| Corresponding Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| Recommended Citation GB/T 7714 | Zhang, Ming-Liang,Zhang, Xu-Yao,Wang, Chuang,et al. Towards prior gap and representation gap for long-tailed recognition[J]. PATTERN RECOGNITION,2023,133:12. |
| APA | Zhang, Ming-Liang,Zhang, Xu-Yao,Wang, Chuang,&Liu, Cheng-Lin.(2023).Towards prior gap and representation gap for long-tailed recognition.PATTERN RECOGNITION,133,12. |
| MLA | Zhang, Ming-Liang,et al."Towards prior gap and representation gap for long-tailed recognition".PATTERN RECOGNITION 133(2023):12. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment