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

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, Dr 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

• Organisation