Zero-shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation

Long, Yang, Liu, Li, Shen, Fumin, Shao, Ling and Li, Xuelong (2018) Zero-shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40 (10). pp. 2498-2512. ISSN 0162-8828

[img]
Preview
PDF (Accepted manuscript) - Submitted Version
Download (9MB) | Preview

Abstract

Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting welllabelled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural language semantics as an intermediate level clue to associate low-level features with high-level classes, in a novel extension of this idea, we aim to synthesise training data for novel classes using only semantic attributes. Despite the simplicity of this idea, there are several challenges. Firstly, how to prevent the synthesised data from over-fitting to training classes Secondly, how to guarantee the synthesised data is discriminative for ZSL tasks Thirdly, we observe that only a few dimensions of the learnt features gain high variances whereas most of the remaining dimensions are not informative. Thus, the question is how to make the concentrated information diffuse to most of the dimensions of synthesised data. To address the above issues, we propose a novel embedding algorithm named Unseen Visual Data Synthesis (UVDS) that projects semantic features to the high-dimensional visual feature space. Two main techniques are introduced in our proposed algorithm.

Item Type: Article
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: Pure Connector
Date Deposited: 24 Oct 2017 05:08
Last Modified: 22 Jul 2020 01:50
URI: https://ueaeprints.uea.ac.uk/id/eprint/65217
DOI: 10.1109/TPAMI.2017.2762295

Actions (login required)

View Item View Item