University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Transductive multi-label zero-shot learning

Fu, Yanwei, Yang, Yongxin, Hospedales, Timothy, Xiang, Tao and Gong, Shaogang (2014) Transductive multi-label zero-shot learning In: British Machine Vision Conference (BMVC), 2014-09-01 - 2014-09-05, Nottingham, UK.

[img]
Preview
Text
YY_paper083.pdf - Accepted version Manuscript

Download (490kB) | Preview

Abstract

Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems. These methods have achieved great success via learning intermediate semantic representations in the form of attributes and more recently, semantic word vectors. However, they have thus far been constrained to the single-label case, in contrast to the growing popularity and importance of more realistic multi-label data. In this paper, for the first time, we investigate and formalise a general framework for multi-label zero-shot learning, addressing the unique challenge therein: how to exploit multi-label correlation at test time with no training data for those classes? In particular, we propose (1) a multi-output deep regression model to project an image into a semantic word space, which explicitly exploits the correlations in the intermediate semantic layer of word vectors; (2) a novel zero-shot learning algorithm for multi-label data that exploits the unique compositionality property of semantic word vector representations; and (3) a transductive learning strategy to enable the regression model learned from seen classes to generalise well to unseen classes. Our zero-shot learning experiments on a number of standard multi-label datasets demonstrate that our method outperforms a variety of baselines. © 2014. The copyright of this document resides with its authors.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Fu, Yanwei
Yang, Yongxinyongxin.yang@surrey.ac.uk
Hospedales, Timothy
Xiang, Taot.xiang@surrey.ac.uk
Gong, Shaogang
Editors :
NameEmailORCID
Valstar, Michel
French, Andrew
Pridmore, Tony
Date : September 2014
DOI : /10.5244/C.28.7
Copyright Disclaimer : c 2014. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Uncontrolled Keywords : Computer vision, Mathematical models, Regression analysis, Vector spaces, Compositionality, Multi-output, Regression model, Semantic layer, Semantic representation, Training data, Transductive learning, Word vectors, Semantics
Depositing User : Diane Maxfield
Date Deposited : 16 Apr 2019 13:56
Last Modified : 16 Apr 2019 13:56
URI: http://epubs.surrey.ac.uk/id/eprint/851675

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800