eprintid: 10198870
rev_number: 7
eprint_status: archive
userid: 699
dir: disk0/10/19/88/70
datestamp: 2024-10-24 15:19:09
lastmod: 2024-10-24 15:19:09
status_changed: 2024-10-24 15:19:09
type: article
metadata_visibility: show
sword_depositor: 699
creators_name: Li, Xiaoxu
creators_name: Wang, Xiangyang
creators_name: Zhu, Rui
creators_name: Ma, Zhanyu
creators_name: Cao, Jie
creators_name: Xue, Jing-Hao
title: Selectively augmented attention network for few-shot image classification
ispublished: pub
divisions: UCL
divisions: B04
divisions: C06
divisions: F61
keywords: Few-shot image classification, 
Data augmentation, 
Attention mechanism, 
Metric-based methods
note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
abstract: Few-shot image classification is a challenging task that aims to learn from a limited number of labelled training images a classification model that can be generalised to unseen classes. Two strategies are usually taken to improve the classification performances of few-shot image classifiers: either applying data augmentation to enlarge the sample size of the training set and reduce overfitting, or involving attention mechanisms to highlight discriminative spatial regions or channels. However, naively applying them to few-shot classifiers directly and separately may lead to undesirable results; for example, some augmented images may focus majorly on the background rather than the object, which brings additional noises to the training process. In this paper, we propose a unified framework, the selectively augmented attention (SAA) network, that carefully integrates the best of the two approaches in an end-to-end fashion via a selective best match module to select the most representative images from the augmented training set. The selected images tend to concentrate on the objects with less irrelevant background, which can assist the subsequent calculation of attentions by alleviating the interference from background. Moreover, we design a joint attention module to jointly learn both the spatial and channel-wise attentions. Experimental results on four benchmark datasets showcase the superior classification performance of the proposed SAA network compared with the state-of-the-arts.
date: 2024-10-14
date_type: published
publisher: Institute of Electrical and Electronics Engineers (IEEE)
official_url: https://doi.org/10.1109/TCSVT.2024.3480279
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 2329447
doi: 10.1109/tcsvt.2024.3480279
lyricists_name: Xue, Jinghao
lyricists_id: JXUEX60
actors_name: Flynn, Bernadette
actors_id: BFFLY94
actors_role: owner
full_text_status: public
publication: IEEE Transactions on Circuits and Systems for Video Technology
issn: 1051-8215
citation:        Li, Xiaoxu;    Wang, Xiangyang;    Zhu, Rui;    Ma, Zhanyu;    Cao, Jie;    Xue, Jing-Hao;      (2024)    Selectively augmented attention network for few-shot image classification.                   IEEE Transactions on Circuits and Systems for Video Technology        10.1109/tcsvt.2024.3480279 <https://doi.org/10.1109/tcsvt.2024.3480279>.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/10198870/1/Selectively_augmented_attention_network_for_few-shot_image_classification.pdf