From Zero-Shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis

Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable. In this paper, we propose a new Zero-shot learning (ZSL) fr...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 6165 - 6174
Main Authors Yang Long, Li Liu, Ling Shao, Fumin Shen, Guiguang Ding, Jungong Han
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2017
Subjects
Computer vision
Feature extraction
Predictive models
Semantics
Training
Visualization
Online AccessGet full text

Cover

More Information
Summary:Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable. In this paper, we propose a new Zero-shot learning (ZSL) framework that can synthesise visual features for unseen classes without acquiring real images. Using the proposed Unseen Visual Data Synthesis (UVDS) algorithm, semantic attributes are effectively utilised as an intermediate clue to synthesise unseen visual features at the training stage. Hereafter, ZSL recognition is converted into the conventional supervised problem, i.e. the synthesised visual features can be straightforwardly fed to typical classifiers such as SVM. On four benchmark datasets, we demonstrate the benefit of using synthesised unseen data. Extensive experimental results manifest that our proposed approach significantly improve the state-of-the-art results.
ISSN:1063-6919
DOI:10.1109/CVPR.2017.653