Few-shot image classification with multi-facet prototypes

Yan, Kun, Bouraoui, Zied, Wang, Ping, Jameel, Shoaib and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2021. Few-shot image classification with multi-facet prototypes. Presented at: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021), Toronto, ON, Canada, 6-11 June 2021. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 1740-1744. 10.1109/ICASSP39728.2021.9414374

Preview

PDF - Accepted Post-Print Version Download (209kB) | Preview

Abstract

The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples. A central challenge is that the available training examples are normally insufficient to determine which visual features are most characteristic of the considered categories. To address this challenge, we organise these visual features into facets, which intuitively group features of the same kind (e.g. features that are relevant to shape, color, or texture). This is motivated from the assumption that (i) the importance of each facet differs from category to category and (ii) it is possible to predict facet importance from a pre-trained embedding of the category names. In particular, we propose an adaptive similarity measure, relying on predicted facet importance weights for a given set of categories. This measure can be used in combination with a wide array of existing metric-based methods. Experiments on miniImageNet and CUB show that our approach improves the state-of-the-art in metric-based FSL.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Additional Information:	"© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works."
Publisher:	IEEE
ISBN:	9781728176055
ISSN:	2379-190X
Date of First Compliant Deposit:	17 March 2021
Date of Acceptance:	30 January 2021
Last Modified:	09 Nov 2022 10:31
URI:	https://orca.cardiff.ac.uk/id/eprint/139750

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item