City Research Online

A simple scheme to amplify inter-class discrepancy for improving few-shot fine-grained image classification

Li, X., Guo, Z., Zhu, R. ORCID: 0000-0002-9944-0369 , Ma, Z., Guo, J. & Xue, J-H. (2024). A simple scheme to amplify inter-class discrepancy for improving few-shot fine-grained image classification. Pattern Recognition, 156, article number 110736. doi: 10.1016/j.patcog.2024.110736


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

Publication Type: Article
Additional Information: © 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (
Publisher Keywords: Few-shot learning, Fine-grained image classification, Metric-based methods
Subjects: H Social Sciences > HF Commerce
Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: Bayes Business School
Bayes Business School > Actuarial Science & Insurance
SWORD Depositor:
[thumbnail of 1-s2.0-S0031320324004874-main.pdf]
Text - Accepted Version
Available under License Creative Commons: Attribution International Public License 4.0.

Download (2MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login