Coarse-to-Fine Description for Fine-Grained Visual Categorization

doi:10.1109/TIP.2016.2599102

	Coarse-to-Fine Description for Fine-Grained Visual Categorization
	Yao, Hantao 1,2; Zhang, Shiliang 3; Zhang, Yongdong 1,4; Li, Jintao 1; Tian, Qi 5
	2016-10-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	25 期号:10 页码:4858-4872
摘要	Recent years have witnessed the significant advance in fine-grained visual categorization, which targets to classify the objects belonging to the same species. To capture enough subtle visual differences and build discriminative visual description, most of the existing methods heavily rely on the artificial part annotations, which are expensive to collect in real applications. Motivated to conquer this issue, this paper proposes a multilevel coarse-to-fine object description. This novel description only requires the original image as input, but could automatically generate visual descriptions discriminative enough for fine-grained visual categorization. This description is extracted from five sources representing coarse-to-fine visual clues: 1) original image is used as the source of global visual clue; 2) object bounding boxes are generated using convolutional neural network (CNN); 3) with the generated bounding box, foreground is segmented using the proposed k nearest neighbour-based co-segmentation algorithm; and 4) two types of part segmentations are generated by dividing the foreground with an unsupervised part learning strategy. The final description is generated by feeding these sources into CNN models and concatenating their outputs. Experiments on two public benchmark data sets show the impressive performance of this coarse-to-fine description, i.e., classification accuracy achieves 82.5% on CUB-200-2011, and 86.9% on fine-grained visual categorization-Aircraft, respectively, which outperform many recent works.
DOI	10.1109/TIP.2016.2599102
收录类别	SCI
语种	英语
资助项目	National High Technology Research and Development Program of China[2014AA015202] ; National Nature Science Foundation of China[61525206] ; National Nature Science Foundation of China[61428207] ; National Nature Science Foundation of China[61572050] ; National Nature Science Foundation of China[91538111] ; National Nature Science Foundation of China[61429201] ; Beijing Advanced Innovation Center for Imaging Technology[BAICIT-2016009] ; ARO[W911NF-15-1-0290] ; Faculty Research Gift Awards by 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:000382677700009
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：65[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/2XEOYT63/8064
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
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, 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.Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Technol, Beijing 100048, 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,Zhang, Yongdong,et al. Coarse-to-Fine Description for Fine-Grained Visual Categorization[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016,25(10):4858-4872.
APA	Yao, Hantao,Zhang, Shiliang,Zhang, Yongdong,Li, Jintao,&Tian, Qi.(2016).Coarse-to-Fine Description for Fine-Grained Visual Categorization.IEEE TRANSACTIONS ON IMAGE PROCESSING,25(10),4858-4872.
MLA	Yao, Hantao,et al."Coarse-to-Fine Description for Fine-Grained Visual Categorization".IEEE TRANSACTIONS ON IMAGE PROCESSING 25.10(2016):4858-4872.