City Research Online

Locally-Enriched Cross-Reconstruction for Few-Shot Fine-Grained Image Classification

Liu, X., Song, Q., Wu, J. , Zhu, R. ORCID: 0000-0002-9944-0369, Ma, Z. & Xue, J. (2023). Locally-Enriched Cross-Reconstruction for Few-Shot Fine-Grained Image Classification. IEEE Transactions on Circuits and Systems for Video Technology, 33(12), pp. 7530-7540. doi: 10.1109/tcsvt.2023.3275382


Few-shot fine-grained image classification has attracted considerable attention in recent years for its realistic setting to imitate how humans conduct recognition tasks. Metricbased few-shot classifiers have achieved high accuracies. However, their metric function usually requires two arguments of vectors, while transforming or reshaping three-dimensional feature maps to vectors can result in loss of spatial information. Image reconstruction is thus involved to retain more appearance details: the test images are reconstructed by different classes and then classified to the one with the smallest reconstruction error. However, discriminative local information, vital to distinguish sub-categories in fine-grained images with high similarities, is not well elaborated when only the base features from a usual embedding module are adopted for reconstruction. Hence, we propose the novel local content-enriched cross-reconstruction network (LCCRN) for few-shot fine-grained classification. In LCCRN, we design two new modules: the local content-enriched module (LCEM) to learn the discriminative local features, and the crossreconstruction module (CRM) to fully engage the local features with the appearance details obtained from a separate embedding module. The classification score is calculated based on the weighted sum of reconstruction errors of the cross-reconstruction tasks, with weights learnt from the training process. Extensive experiments on four fine-grained datasets showcase the superior classification performance of LCCRN compared with the stateof-the-art few-shot classification methods. Codes are available at:

Publication Type: Article
Additional Information: © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Publisher Keywords: Few-shot image classification, fine-grained image classification, discriminative local features, ridge regression, image reconstruction
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Departments: Bayes Business School > Actuarial Science & Insurance
SWORD Depositor:
[thumbnail of FINAL VERSION.pdf]
Text - Accepted Version
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