Li, Xiaoxu;
Wang, Lang;
Zhu, Rui;
Ma, Zhanyu;
Cao, Jie;
Xue, Jing-Hao;
(2025)
SRML: Structure-relation mutual learning network for few-shot image classification.
Pattern Recognition
, 168
, Article 111822. 10.1016/j.patcog.2025.111822.
Preview |
Text
1-s2.0-S0031320325004820-main.pdf - Published Version Download (2MB) | Preview |
Abstract
Few-shot image classification aims at tackling a challenging but practical classification setting, where only few labelled images are available for training. Metric-based methods are main-stream solutions for few-shot image classification, but many of them extract features that are either irrelevant to target objects in the query images or insufficient to describe the local shape or structural patterns within images, which can lead to mis-identification of the target objects, especially when the images are of multiple objects. To resolve this issue, we propose the structure-relation mutual learning (SRML) network, which first learns both the intra-image structural features and the inter-image relational features in a parallel fashion via two parallel branches, the structural feature extractor (SFE) and the relational feature extractor (RFE), and then harnesses mutual learning to enable knowledge exchange between them. In such a manner, the structural features learnt from the SFE branch not only contain the structural patterns within the images, but also focus more on the target objects, guided by the relational knowledge from the RFE branch. In return, the RFE branch can exploit the more-focused structural knowledge to better match the target objects in the support and query images. We conduct extensive experiments on four few-shot classification benchmark datasets to showcase the superior classification of the proposed SRML network, achieving a 3.17% improvement in classification accuracy over the leading competitor, RENet Kang et al. (2021). The code of this work can be found in https://github.com/Rilliant7/SRML.
| Type: | Article |
|---|---|
| Title: | SRML: Structure-relation mutual learning network for few-shot image classification |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.patcog.2025.111822 |
| Publisher version: | https://doi.org/10.1016/j.patcog.2025.111822 |
| Language: | English |
| Additional information: | © 2025 The Authors. 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 image classification, Self-correlation, Cross-correlation, Mutual learning |
| 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/10208723 |
Archive Staff Only
 |
View Item |
