Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection

doi:10.1109/TIP.2024.3482182

	Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection
	Yu, Zhipeng 1; Xu, Qianqian 2; Jiang, Yangbangyan 3; Sun, Yingfei 1; Huang, Qingming 2,3
	2024
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	33 页码:6083-6097
摘要	The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive pairs for noisy samples to enhance the sample utilization. Specifically, SGPS first effectively identifies clean and noisy samples by a probability-based clean sample selectionstrategy. To further utilize the remaining noisy samples, we discover their potential similar samples based on the subgroup information given by a subgroup generation module and then aggregate them into informative positive prototypes for each noisy sample via a positive prototype generation module. Afterward, a new contrastive loss is tailored for the noisy samples with their selected positive pairs. SGPS can be easily integrated into the training process of existing pair-wise DML tasks, like image retrieval and face recognition. Extensive experiments on multiple synthetic and real-world large-scale label noise datasets demonstrate the effectiveness of our proposed method. Without any bells and whistles, our SGPS framework outperforms the state-of-the-art noisy label DML methods.
关键词	Metric learning noisy label deep learning deep learning pair- wise loss pair- wise loss pair- wise loss pair- wise loss positive-pair selection positive-pair selection
DOI	10.1109/TIP.2024.3482182
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0102000] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[U23B2051] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[62122075] ; National Natural Science Foundation of China[62406305] ; National Natural Science Foundation of China[62471013] ; National Natural Science Foundation of China[62476068] ; National Natural Science Foundation of China[62272439] ; Youth Innovation Promotion Association CAS ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0680000] ; Innovation Funding of Institute of Computing Technology (ICT), CAS[E000000] ; China Postdoctoral Science Foundation (CPSF)[2023M743441] ; Postdoctoral Fellowship Program of CPSF[GZB20230732]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001342519900005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39460
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Jiang, Yangbangyan; Sun, Yingfei
作者单位	1.Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Yu, Zhipeng,Xu, Qianqian,Jiang, Yangbangyan,et al. Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:6083-6097.
APA	Yu, Zhipeng,Xu, Qianqian,Jiang, Yangbangyan,Sun, Yingfei,&Huang, Qingming.(2024).Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,6083-6097.
MLA	Yu, Zhipeng,et al."Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):6083-6097.