Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling

doi:10.1109/TPAMI.2024.3432099

	Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling
	Zhang, Beichen 1,2; Li, Liang 3; Wang, Shuhui 3; Cai, Shaofei 3; Zha, Zheng-Jun 4; Tian, Qi 5; Huang, Qingming 1,6
	2024-12-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	46 期号:12 页码:9780-9796
摘要	Active learning (AL) is to design label-efficient algorithms by labeling the most representative samples. It reduces annotation cost and attracts increasing attention from the community. However, previous AL methods suffer from the inadequacy of annotations and unreliable uncertainty estimation. Moreover, we find that they ignore the intra-diversity of selected samples, which leads to sampling redundancy. In view of these challenges, we propose an inductive state-relabeling adversarial AL model (ISRA) that consists of a unified representation generator, an inductive state-relabeling discriminator, and a heuristic clique rescaling module. The generator introduces contrastive learning to leverage unlabeled samples for self-supervised training, where the mutual information is utilized to improve the representation quality for AL selection. Then, we design an inductive uncertainty indicator to learn the state score from labeled data and relabel unlabeled data with different importance for better discrimination of instructive samples. To solve the problem of sampling redundancy, the heuristic clique rescaling module measures the intra-diversity of candidate samples and recurrently rescales them to select the most informative samples. The experiments conducted on eight datasets and two imbalanced scenarios show that our model outperforms the previous state-of-the-art AL methods. As an extension on the cross-modal AL task, we apply ISRA to the image captioning and it also achieves superior performance.
关键词	Active learning adversarial learning state relabeling contrastive learning data diversity
DOI	10.1109/TPAMI.2024.3432099
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102000] ; National Natural Science Foundation of China[62322211] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[62336008] ; National Natural Science Foundation of China[U21B2038] ; National Natural Science Foundation of China[62225207] ; National Natural Science Foundation of China[2024C01023] ; Ministry of Culture and Tourism[2023DMKLB004]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001364431200145
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41083
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Liang; Huang, Qingming
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 2.Harbin Inst Technol, Sch Comp Sci & Technol, Weihai 264209, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230027, Peoples R China 5.Huawei Technol, Cloud BU, Shenzhen 518129, Peoples R China 6.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Beichen,Li, Liang,Wang, Shuhui,et al. Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2024,46(12):9780-9796.
APA	Zhang, Beichen.,Li, Liang.,Wang, Shuhui.,Cai, Shaofei.,Zha, Zheng-Jun.,...&Huang, Qingming.(2024).Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,46(12),9780-9796.
MLA	Zhang, Beichen,et al."Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46.12(2024):9780-9796.