DSP: Discriminative Spatial Part modeling for Fine-Grained Visual Categorization

doi:10.1016/j.imavis.2017.05.003

	DSP: Discriminative Spatial Part modeling for Fine-Grained Visual Categorization
	Yao, Hantao 1,2; Zhang, Dongming 3; Li, Jintao 1; Zhou, Jianshe 4; Zhang, Shiliang 5; Zhang, Yongdong 1,2
	2017-07-01
发表期刊	IMAGE AND VISION COMPUTING
ISSN	0262-8856
卷号	63 页码:24-37
摘要	Different from the basic-level classification, the Fine-Grained Visual Categorization (FGVC) aims to classify objects belonging to the same species. Therefore, it is more challenging than the basic-level classification. Recently, significant advances have been achieved in FGVC. However, most of the existing methods require bounding boxes or part annotations for training and testing, resulting in limited usability and flexibility. To conquer these limitations, we aim to automatically detect the bounding boxes and parts for FGVC. The bounding boxes are acquired by transferring bounding boxes from training images to testing images. Based on the generated bounding boxes, we employ a multiple-layer Orientational Spatial Part (OSP) model to learn local parts for the object. To achieve more discriminative part modeling, the Discriminative Spatial Part (DSP) model is proposed to select the discriminative parts from OSP. Finally, we employ Convolutional Neural Network (CNN) as the feature extractor and train a linear SVM as the classifier. Extensive experiments on public benchmark datasets manifest the impressive performance of our method, i.e., classification accuracy achieves 79.8% on CUB-200-2011 and 85.7% on Aircraft, which are higher than many existing methods using manual annotations. (C) 2017 Elsevier B.V. All rights reserved.
关键词	Orientational Spatial Part model Discriminative Spatial Part modeling Fine-Grained Visual Categorization CNN
DOI	10.1016/j.imavis.2017.05.003
收录类别	SCI
语种	英语
资助项目	National Nature Science Foundation of China (NSFC)[61525206] ; National Nature Science Foundation of China (NSFC)[61672495] ; National Nature Science Foundation of China (NSFC)[61572050] ; National Nature Science Foundation of China (NSFC)[91538111] ; National Nature Science Foundation of China (NSFC)[61620106009] ; National Key Research and Development Plan of China[2016YFB0801203] ; National Key Research and Development Plan of China[2016YFB0801200]
WOS研究方向	Computer Science ; Engineering ; Optics
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Optics
WOS记录号	WOS:000404312400003
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：5[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/2XEOYT63/7116
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, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Coordinat Ctr China, Natl Comp Network Emergency Response Tech Team, Beijing 100029, Peoples R China 4.Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Technol, Beijing 100048, Peoples R China 5.Peking Univ, Elect Engn & Comp Sci, Beijing 100871, Peoples R China
推荐引用方式 GB/T 7714	Yao, Hantao,Zhang, Dongming,Li, Jintao,et al. DSP: Discriminative Spatial Part modeling for Fine-Grained Visual Categorization[J]. IMAGE AND VISION COMPUTING,2017,63:24-37.
APA	Yao, Hantao,Zhang, Dongming,Li, Jintao,Zhou, Jianshe,Zhang, Shiliang,&Zhang, Yongdong.(2017).DSP: Discriminative Spatial Part modeling for Fine-Grained Visual Categorization.IMAGE AND VISION COMPUTING,63,24-37.
MLA	Yao, Hantao,et al."DSP: Discriminative Spatial Part modeling for Fine-Grained Visual Categorization".IMAGE AND VISION COMPUTING 63(2017):24-37.