CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning
Peng PX(彭佩玺)1; Tian YH(田永鸿)1; Tao Xiang2; Wang YW(王耀威)1; Massimiliano Pontil3; Huang TJ(黄铁军)1
Source PublicationIEEE Transactions on Pattern Analysis and Machine Intelligence
2017
Issue99Pages:1-1
AbstractA number of vision problems such as zero-shot learning and person re-identification can be considered as cross-class transfer learning problems. As mid-level semantic properties shared cross different object classes, attributes have been studied extensively for knowledge-transfer across classes. Most previous attribute learning methods focus only on human-defined/nameable semantic attributes, whilst ignoring the fact there also exist undefined/latent shareable visual properties, or latent attributes. These latent attributes can be either discriminative or non-discriminative parts depending on whether they can contribute to an object recognition task. In this work, we argue that learning the latent attributes jointly with user-defined semantic attributes not only leads to better representation but also helps semantic attribute prediction. A novel dictionary learning model is proposed which decomposes the dictionary space into three parts corresponding to semantic, latent discriminative and latent background attributes respectively. Such a joint attribute learning model is then extended following a multi-task transfer learning framework to address a more challenging unsupervised domain adaptation problem, where annotations are only available on an auxiliary dataset and the target dataset is unlabelled. Extensive experiments show that our models, though being linear and thus extremely efficient to compute, produce state-of-the-art results on both zero-shot learning and person re-identification.
KeywordAttribute Learning Dictionary Learning Multi-task Learning Zero-shot Learning Person Re-identification Transfer Learning
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20212
Collection模式识别国家重点实验室_视频内容安全
Affiliation1.北京大学
2.Queen Mary, University of London
3.University College London
Recommended Citation
GB/T 7714
Peng PX,Tian YH,Tao Xiang,et al. Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017(99):1-1.
APA Peng PX,Tian YH,Tao Xiang,Wang YW,Massimiliano Pontil,&Huang TJ.(2017).Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning.IEEE Transactions on Pattern Analysis and Machine Intelligence(99),1-1.
MLA Peng PX,et al."Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning".IEEE Transactions on Pattern Analysis and Machine Intelligence .99(2017):1-1.
Files in This Item: Download All
File Name/Size DocType Version Access License
Joint Semantic and L(2373KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Peng PX(彭佩玺)]'s Articles
[Tian YH(田永鸿)]'s Articles
[Tao Xiang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Peng PX(彭佩玺)]'s Articles
[Tian YH(田永鸿)]'s Articles
[Tao Xiang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peng PX(彭佩玺)]'s Articles
[Tian YH(田永鸿)]'s Articles
[Tao Xiang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learnin.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.