Knowledge Commons of Institute of Automation,CAS
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 | |
发表期刊 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
2018 | |
卷号 | 40期号:7页码:1625-1638 |
摘要 | A 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. |
关键词 | Attribute Learning Dictionary Learning Multi-task Learning Zero-shot Learning Person Re-identification Transfer Learning |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/20212 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
作者单位 | 1.北京大学 2.Queen Mary, University of London 3.University College London |
推荐引用方式 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,2018,40(7):1625-1638. |
APA | Peng PX,Tian YH,Tao Xiang,Wang YW,Massimiliano Pontil,&Huang TJ.(2018).Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning.IEEE Transactions on Pattern Analysis and Machine Intelligence,40(7),1625-1638. |
MLA | Peng PX,et al."Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning".IEEE Transactions on Pattern Analysis and Machine Intelligence 40.7(2018):1625-1638. |
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 | ||
Joint Semantic and L(2373KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论