Anti-Noise Relation Network for Few-shot Learning

Li, X., Yan, J., Wu, J., Liu, Y., Yang, X. and Ma, Z. (2020) Anti-Noise Relation Network for Few-shot Learning. In: 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Auckland, New Zealand, 07-10 Dec 2020, pp. 1719-1724. ISBN 9789881476883

[img] Text
225913.pdf - Accepted Version

1MB

Publisher's URL: https://ieeexplore.ieee.org/document/9306437

Abstract

Few-shot classification has received great attention in the field of machine learning and computer vision. It aims is to achieve the learning ability close to human recognition by training from a few labelled samples. The existing few-shot classification methods have attempted to alleviate the impact of insufficient samples in a variety of ways, such as meta-learning and metric learning, but they ignore the noise robustness. This work proposes a new Anti-Noise Relation Network by embedding an autoencoder network into a classical neural network of fewshot classification, Relation Network. Experimental results on the Stanford Car and CUB-200-2011 datasets demonstrate the superiority of the proposed method in both classification accuracy and robustness against different noises.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Yang, Ms Xiaochen
Authors: Li, X., Yan, J., Wu, J., Liu, Y., Yang, X., and Ma, Z.
College/School:College of Science and Engineering > School of Mathematics and Statistics > Statistics
ISSN:2640-0103
ISBN:9789881476883
Copyright Holders:Copyright © 2020 APSIPA
First Published:First published in 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC): 1719-1724
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record