Research Repository

Few-shot image classification with multi-facet prototypes

Yan, Kun and Bouraoui, Zied and Wang, Ping and Jameel, Shoaib and Schockaert, Steven (2021) Few-shot image classification with multi-facet prototypes. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, 2021-06-06 - 2021-06-11, Online. (In Press)

ICASSP2021_paper.pdf - Accepted Version

Download (208kB) | Preview


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, colour, 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.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Uncontrolled Keywords: Few-shot learning; multi-facet representations; metric-based learning; BERT
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 02 Feb 2021 14:59
Last Modified: 15 Jan 2022 01:36

Actions (login required)

View Item View Item