AutoBD: Automated Bi-Level Description for Scalable Fine-Grained Visual Categorization

doi:10.1109/TIP.2017.2751960

	AutoBD: Automated Bi-Level Description for Scalable Fine-Grained Visual Categorization
	Yao, Hantao 1,2; Zhang, Shiliang 3; Yan, Chenggang 4; Zhang, Yongdong 1,2; Li, Jintao 1; Tian, Qi 5
	2018
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	27 期号:1 页码:10-23
摘要	Compared with traditional image classification, fine-grained visual categorization is a more challenging task, because it targets to classify objects belonging to the same species, e.g., classify hundreds of birds or cars. In the past several years, researchers have made many achievements on this topic. However, most of them are heavily dependent on the artificial annotations, e.g., bounding boxes, part annotations, and so on. The requirement of artificial annotations largely hinders the scalability and application. Motivated to release such dependence, this paper proposes a robust and discriminative visual description named Automated Bi-level Description (AutoBD). "Bi-level" denotes two complementary part-level and object-level visual descriptions, respectively. AutoBD is "automated," because it only requires the image-level labels of training images and does not need any annotations for testing images. Compared with the part annotations labeled by the human, the image-level labels can be easily acquired, which thus makes AutoBD suitable for large-scale visual categorization. Specifically, the part-level description is extracted by identifying the local region saliently representing the visual distinctiveness. The object-level description is extracted from object bounding boxes generated with a co-localization algorithm. Although only using the image-level labels, AutoBD outperforms the recent studies on two public benchmark, i.e., classification accuracy achieves 81.6% on CUB-200-2011 and 88.9% on Car-196, respectively. On the large-scale Birdsnap data set, AutoBD achieves the accuracy of 68%, which is currently the best performance to the best of our knowledge.
DOI	10.1109/TIP.2017.2751960
收录类别	SCI
语种	英语
资助项目	National Nature Science Foundation of China[61525206] ; National Nature Science Foundation of China[61572050] ; National Nature Science Foundation of China[91538111] ; National Nature Science Foundation of China[61429201] ; National Nature Science Foundation of China[61428207] ; Beijing Advanced Innovation Center for Imaging Technology[BAICIT-2016009] ; ARO[W911NF-15-1-0290] ; NEC Laboratories of America ; Blippar
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000413256300001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：35[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/6878
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Yongdong; Tian, Qi
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Peking Univ, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China 4.Hangzhou Dianzi Univ, Sch Inst Informat & Control, Hangzhou 541004, Zhejiang, Peoples R China 5.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
推荐引用方式 GB/T 7714	Yao, Hantao,Zhang, Shiliang,Yan, Chenggang,et al. AutoBD: Automated Bi-Level Description for Scalable Fine-Grained Visual Categorization[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(1):10-23.
APA	Yao, Hantao,Zhang, Shiliang,Yan, Chenggang,Zhang, Yongdong,Li, Jintao,&Tian, Qi.(2018).AutoBD: Automated Bi-Level Description for Scalable Fine-Grained Visual Categorization.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(1),10-23.
MLA	Yao, Hantao,et al."AutoBD: Automated Bi-Level Description for Scalable Fine-Grained Visual Categorization".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.1(2018):10-23.