CASIA OpenIR  > 智能感知与计算研究中心
Large-Scale Weakly Supervised Object Localization via Latent Category Learning
Wang, Chong1; Huang, Kaiqi1; Ren, Weiqiang1; Zhang, Junge1; Maybank, Steve2
2015-04-01
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
卷号24期号:4页码:1371-1385
文章类型Article
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.
关键词Weakly Supervised Learning Object Localization Latent Semantic Analysis Large-scale
WOS标题词Science & Technology ; Technology
关键词[WOS]IMAGE CLASSIFICATION ; NETWORKS
收录类别SCI
语种英语
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000351088600004
引用统计
被引频次:17[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/8086
专题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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Chong Wang_Large-Sca(5133KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Chong]的文章
[Huang, Kaiqi]的文章
[Ren, Weiqiang]的文章
百度学术
百度学术中相似的文章
[Wang, Chong]的文章
[Huang, Kaiqi]的文章
[Ren, Weiqiang]的文章
必应学术
必应学术中相似的文章
[Wang, Chong]的文章
[Huang, Kaiqi]的文章
[Ren, Weiqiang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Chong Wang_Large-Scale Weakly Supervised Object Localization via Latent Category Learning.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。