Attribute-Guided Feature Learning for Few-Shot Image Recognition

doi:10.1109/TMM.2020.2993952

	Attribute-Guided Feature Learning for Few-Shot Image Recognition
	Zhu, Yaohui 1,2; Min, Weiqing 1,2; Jiang, Shuqiang 1,2
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2021
卷号	23 页码:1200-1209
关键词	Image recognition Training Task analysis Semantics Standards Measurement Visualization Attribute learning few-shot learning image recognition
ISSN号	1520-9210
DOI	10.1109/TMM.2020.2993952
英文摘要	Few-shot image recognition has become an essential problem in the field of machine learning and image recognition, and has attracted more and more research attention. Typically, most few-shot image recognition methods are trained across tasks. However, these methods are apt to learn an embedding network for discriminative representations of training categories, and thus could not distinguish well for novel categories. To establish connections between training and novel categories, we use attribute-related representations for few-shot image recognition and propose an attribute-guided two-layer learning framework, which is capable of learning general feature representations. Specifically, few-shot image recognition trained over tasks and attribute learning trained over images share the same network in a multi-task learning framework. In this way, few-shot image recognition learns feature representations guided by attributes, and is thus less sensitive to novel categories compared with feature representations only using category supervision. Meanwhile, the multi-layer features associated with attributes are aligned with category learning on multiple levels respectively. Therefore we establish a two-layer learning mechanism guided by attributes to capture more discriminative representations, which are complementary compared with a single-layer learning mechanism. Experimental results on CUB-200, AWA and MiniImageNet datasets demonstrate our method effectively improves the performance.
资助项目	National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61972378] ; National Natural Science Foundation of China[U1936203] ; National Natural Science Foundation of China[U19B2040] ; Beijing Natural Science Foundation[L182054] ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-Notch Young Professionals
WOS研究方向	Computer Science ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000645068200004
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17794]
专题	中国科学院计算技术研究所
通讯作者	Jiang, Shuqiang
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, CAS, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Yaohui,Min, Weiqing,Jiang, Shuqiang. Attribute-Guided Feature Learning for Few-Shot Image Recognition[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021,23:1200-1209.
APA	Zhu, Yaohui,Min, Weiqing,&Jiang, Shuqiang.(2021).Attribute-Guided Feature Learning for Few-Shot Image Recognition.IEEE TRANSACTIONS ON MULTIMEDIA,23,1200-1209.
MLA	Zhu, Yaohui,et al."Attribute-Guided Feature Learning for Few-Shot Image Recognition".IEEE TRANSACTIONS ON MULTIMEDIA 23(2021):1200-1209.