Dual Prototypical Network for Robust Few-shot Image Classification

Song, Q., Peng, Z., Ji, L., Yang, X. and Li, X. (2022) Dual Prototypical Network for Robust Few-shot Image Classification. In: 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Chiang Mai, Thailand, 7-10 November 2022, pp. 533-537. ISBN 9781665486620 (doi: 10.23919/APSIPAASC55919.2022.9979898)

Abstract

Deep neural networks have outperformed humans on some image recognition and classification tasks. However, with the emergence of various novel classes, it remains a chal-lenge to continuously expand the learning capability of such networks from a limited number of labeled samples. Metric-based approaches have been playing a key role in few-shot image classification, but most of them measure the distance between samples in the metric space using only a single metric function. In this paper, we propose a Dual Prototypical Network (DPN) to improve the test-time robustness of the classical prototypical network. The proposed method not only focuses on the distance of the original features, but also adds perturbation noise to the image and calculates the distance of noisy features. By enforcing the model to predict well under both metrics, more representative and robust class prototypes are learned and thus lead to better generalization performance. We validate our method on three fine-grained datasets in both clean and noisy settings.

• Item Type: Conference Proceedings
• Additional Information: This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grant 62176110, 62111530146, 61906080, Young Doctoral Fund of Education Department of Gansu Province under Grant 2021QB-038, Hong-Liu Distinguished Youth Talents Foundation of Lanzhou University of Technology.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Yang, Dr Xiaochen
• Authors: Song, Q., Peng, Z., Ji, L., Yang, X., and Li, X.
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
• College/School: College of Science and Engineering > School of Mathematics and Statistics > Statistics
• ISSN: 2640-009X
• ISBN: 9781665486620
• Copyright Holders: Copyright © 2022 IEEE
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher