UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning

Peng, P; Tian, Y; Xiang, T; Wang, Y; Pontil, M; Huang, T; (2018) Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence , 40 (7) pp. 1625-1638. 10.1109/TPAMI.2017.2723882. Green open access

[thumbnail of Xiang Joint Semantic and Latent 2017 Accepted.pdf]
Preview
Text
Xiang Joint Semantic and Latent 2017 Accepted.pdf - Accepted version

Download (2MB) | Preview

Abstract

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 by 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 completely unlabelled. Extensive experiments show that the proposed 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.

Type: Article
Title: Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/TPAMI.2017.2723882
Publisher version: https://doi.org/10.1109/TPAMI.2017.2723882
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Attribute learning , dictionary learning , multi-task learning , zero-shot learning , person re-identification , transfer learning
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10065515
Downloads since deposit
219Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item