Bidirectional Attention-Recognition Model for Fine-Grained Object Classification

doi:10.1109/TMM.2019.2954747

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 远程智能医疗

	Bidirectional Attention-Recognition Model for Fine-Grained Object Classification
	Liu, Chuanbin 1; Xie, Hongtao 1; Zha, Zhengjun 1; Yu, Lingyun 1; Chen, Zhineng 2; Zhang, Yongdong 1
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2020-07-01
卷号	22 期号:7 页码:1785-1795
关键词	Fine-grained object classification interpretable machine learning visual attention pattern recognition data augmentation
ISSN号	1520-9210
DOI	10.1109/TMM.2019.2954747
通讯作者	Xie, Hongtao(htxie@ustc.edu.cn) ; Zhang, Yongdong(zhyd73@ustc.edu.cn)
英文摘要	Fine-grained object classification (FGOC) is a challenging research topic in multimedia computing with machine learning, which faces two pivotal conundrums: focusing attention on the discriminate part regions, and then processing recognition with the part-based features. Existing approaches generally adopt a unidirectional two-step structure, that first locate the discriminate parts and then recognize the part-based features. However, they neglect the truth that part localization and feature recognition can be reinforced in a bidirectional process. In this paper, we propose a novel bidirectional attention-recognition model (BARM) to actualize the bidirectional reinforcement for FGOC. The proposed BARM consists of one attention agent for discriminate part regions proposing and one recognition agent for feature extraction and recognition. Meanwhile, a feedback flow is creatively established to optimize the attention agent directly by recognition agent. Therefore, in BARM the attention agent and the recognition agent can reinforce each other in a bidirectional way and the overall framework can be trained end-to-end without neither object nor parts annotations. Moreover, a novel Multiple Random Erasing data augmentation is proposed, and it exhibits impressive pertinency and superiority for FGOC. Conducted on several extensive FGOC benchmarks, BARM outperforms the present state-of-the-art methods in classification accuracy. Furthermore, BARM exhibits a clear interpretability and keeps consistent with the human perception in visualization experiments.
资助项目	National Key Research and Development Program of China[2017YFC0820600] ; National Nature Science Foundation of China[61525206] ; National Nature Science Foundation of China[61771468] ; Youth Innovation Promotion Association Chinese Academy of Sciences[2017209]
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:000545990500011
资助机构	National Key Research and Development Program of China ; National Nature Science Foundation of China ; Youth Innovation Promotion Association Chinese Academy of Sciences
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40041]
专题	数字内容技术与服务研究中心_远程智能医疗
通讯作者	Xie, Hongtao; Zhang, Yongdong
作者单位	1.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Liu, Chuanbin,Xie, Hongtao,Zha, Zhengjun,et al. Bidirectional Attention-Recognition Model for Fine-Grained Object Classification[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2020,22(7):1785-1795.
APA	Liu, Chuanbin,Xie, Hongtao,Zha, Zhengjun,Yu, Lingyun,Chen, Zhineng,&Zhang, Yongdong.(2020).Bidirectional Attention-Recognition Model for Fine-Grained Object Classification.IEEE TRANSACTIONS ON MULTIMEDIA,22(7),1785-1795.
MLA	Liu, Chuanbin,et al."Bidirectional Attention-Recognition Model for Fine-Grained Object Classification".IEEE TRANSACTIONS ON MULTIMEDIA 22.7(2020):1785-1795.