中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Large-Scale Weakly Supervised Object Localization via Latent Category Learning

文献类型：期刊论文

作者Wang, Chong1; Huang, Kaiqi1; Ren, Weiqiang1; Zhang, Junge1; Maybank, Steve2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2015-04-01
卷号24期号:4页码:1371-1385
关键词Weakly supervised learning object localization latent semantic analysis large-scale
英文摘要Localizing objects in cluttered backgrounds is challenging under large-scale weakly supervised conditions. Due to the cluttered image condition, objects usually have large ambiguity with backgrounds. Besides, there is also a lack of effective algorithm for large-scale weakly supervised localization in cluttered backgrounds. However, backgrounds contain useful latent information, e.g., the sky in the aeroplane class. If this latent information can be learned, object-background ambiguity can be largely reduced and background can be suppressed effectively. In this paper, we propose the latent category learning (LCL) in large-scale cluttered conditions. LCL is an unsupervised learning method which requires only image-level class labels. First, we use the latent semantic analysis with semantic object representation to learn the latent categories, which represent objects, object parts or backgrounds. Second, to determine which category contains the target object, we propose a category selection strategy by evaluating each category's discrimination. Finally, we propose the online LCL for use in large-scale conditions. Evaluation on the challenging PASCAL Visual Object Class (VOC) 2007 and the large-scale imagenet large-scale visual recognition challenge 2013 detection data sets shows that the method can improve the annotation precision by 10% over previous methods. More importantly, we achieve the detection precision which outperforms previous results by a large margin and can be competitive to the supervised deformable part model 5.0 baseline on both data sets.
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
研究领域[WOS]Computer Science ; Engineering
关键词[WOS]IMAGE CLASSIFICATION ; NETWORKS
收录类别SCI
语种英语
WOS记录号WOS:000351088600004
公开日期2015-09-22
源URL[http://ir.ia.ac.cn/handle/173211/8086]  
专题自动化研究所_智能感知与计算研究中心
作者单位1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.Univ London, Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HU, England
推荐引用方式
GB/T 7714		 Wang, Chong,Huang, Kaiqi,Ren, Weiqiang,et al. Large-Scale Weakly Supervised Object Localization via Latent Category Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2015,24(4):1371-1385.
APA Wang, Chong,Huang, Kaiqi,Ren, Weiqiang,Zhang, Junge,&Maybank, Steve.(2015).Large-Scale Weakly Supervised Object Localization via Latent Category Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,24(4),1371-1385.
MLA Wang, Chong,et al."Large-Scale Weakly Supervised Object Localization via Latent Category Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 24.4(2015):1371-1385.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。