Li, Xiaoxu;
Guo, Zijie;
Zhu, Rui;
Ma, Zhanyu;
Guo, Jun;
Xue, Jing-Hao;
(2024)
A simple scheme to amplify inter-class discrepancy for improving few-shot fine-grained image classification.
Pattern Recognition
, 156
, Article 110736. 10.1016/j.patcog.2024.110736.
Preview |
Text
OA-1-s2.0-S0031320324004874-main.pdf - Published Version Download (2MB) | Preview |
Abstract
Few-shot image classification is a challenging topic in pattern recognition and computer vision. Few-shot fine-grained image classification is even more challenging, due to not only the few shots of labelled samples but also the subtle differences to distinguish subcategories in fine-grained images. A recent method called task discrepancy maximisation (TDM) can be embedded into the feature map reconstruction network (FRN) to generate discriminative features, by preserving the appearance details through reconstructing the query image and then assigning higher weights to more discriminative channels, producing the state-of-the-art performance for few-shot fine-grained image classification. However, due to the small inter-class discrepancy in fine-grained images and the small training set in few-shot learning, the training of FRN+TDM can result in excessively flexible boundaries between subcategories and hence overfitting. To resolve this problem, we propose a simple scheme to amplify inter-class discrepancy and thus improve FRN+TDM. To achieve this aim, instead of developing new modules, our scheme only involves two simple amendments to FRN+TDM: relaxing the inter-class score in TDM, and adding a centre loss to FRN. Extensive experiments on five benchmark datasets showcase that, although embarrassingly simple, our scheme is quite effective to improve the performance of few-shot fine-grained image classification. The code is available at https://github.com/Airgods/AFRN.git.
| Type: | Article |
|---|---|
| Title: | A simple scheme to amplify inter-class discrepancy for improving few-shot fine-grained image classification |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.patcog.2024.110736 |
| Publisher version: | https://doi.org/10.1016/j.patcog.2024.110736 |
| Language: | English |
| Additional information: | © 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
| Keywords: | Few-shot learning, Fine-grained image classification, Metric-based methods |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10205775 |
Archive Staff Only
 |
View Item |
