Li, X;
Ding, S;
Xie, J;
Yang, X;
Ma, Z;
Xue, JH;
(2025)
CDN4: A cross-view Deep Nearest Neighbor Neural Network for fine-grained few-shot classification.
Pattern Recognition
, 163
, Article 111466. 10.1016/j.patcog.2025.111466.
Preview |
Text
OA-1-s2.0-S0031320325001268-main.pdf - Published Version Download (2MB) | Preview |
Abstract
The fine-grained few-shot classification is a challenging task in computer vision, aiming to classify images with subtle and detailed differences given scarce labeled samples. A promising avenue to tackle this challenge is to use spatially local features to densely measure the similarity between query and support samples. Compared with image-level global features, local features contain more low-level information that is rich and transferable across categories. However, methods based on spatially localized features have difficulty distinguishing subtle category differences due to the lack of sample diversity. To address this issue, we propose a novel method called Cross-view Deep Nearest Neighbor Neural Network (CDN4). CDN4 applies a random geometric transformation to augment a different view of support and query samples and subsequently exploits four similarities between the original and transformed views of query local features and those views of support local features. The geometric augmentation increases the diversity between samples of the same class, and the cross-view measurement encourages the model to focus more on discriminative local features for classification through the cross-measurements between the two branches. Extensive experiments validate the superiority of CDN4, which achieves new state-of-the-art results in few-shot classification across various fine-grained benchmarks. Code is available at.
| Type: | Article |
|---|---|
| Title: | CDN4: A cross-view Deep Nearest Neighbor Neural Network for fine-grained few-shot classification |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.patcog.2025.111466 |
| Publisher version: | https://doi.org/10.1016/j.patcog.2025.111466 |
| 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 learning, Fine-grained image classification, Deep neural network, Data augmentation |
| 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/10205773 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
