A Fine-Grained Car Recognition Method Based on a Lightweight Attention Network and Regularized Fine-Tuning
Electronics · 06.01.2025 · 14 (1) · 211
DOI: 10.3390/electronics14010211 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 06.01.2025. Verfasst von Cheng Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: “Pioneer” and “Leading Goose” R&D Program of Zhejiang.
Abstract (Originalsprache)
Car fine recognition is a typical scenario for fine-grained image classification, which has great research and application value in both civilian and military fields. However, current research on fine-grained classification is often limited to improving the accuracy of classification models, ignoring the need for lightweight and efficient applications in practical applications, resulting in a disconnect from reality. In this paper, a fine-grained car recognition method based on a lightweight attention network and regularized fine-tuning is proposed. Based on the high-performance, lightweight convolutional neural network (CNN) architecture MobileNet V3, an improved CNN architecture HAM-MobileNet that includes a hybrid attention module is designed. A regularized fine-tuning strategy that includes correlation constraints is adopted. By fine-tuning the HAM-MobileNet, accurate classification of car images can be achieved. The experimental results on the Stanford cars dataset show that the proposed method achieves an accuracy rate of 84.6%, which is the highest level among all lightweight CNN architectures and is comparable to non-lightweight CNN architectures. The visualization results show that the proposed hybrid attention module can make the network model focus more on the target objects with consistent classes, suppress task-irrelevant backgrounds and other noise, and improve the learning ability and generalization of the network model.
Förderung
- “Pioneer” and “Leading Goose” R&D Program of Zhejiang
Zitieren
APA
Zhang, C., Li, Q., Liu, C., Zhang, Y., Zhao, D., Ji, C., & Wang, J. (2025). A Fine-Grained Car Recognition Method Based on a Lightweight Attention Network and Regularized Fine-Tuning. Electronics, 14(1), 211. https://doi.org/10.3390/electronics14010211
Vancouver
Zhang C, Li Q, Liu C, Zhang Y, Zhao D, Ji C, et al. A Fine-Grained Car Recognition Method Based on a Lightweight Attention Network and Regularized Fine-Tuning. Electronics. 2025;14(1):211. doi:10.3390/electronics14010211
BibTeX
@article{Zhang2025,
author = {Zhang, Cheng and Li, Qiaochu and Liu, Chang and Zhang, Yi and Zhao, Ding and Ji, Chao and Wang, Jin},
title = {A Fine-Grained Car Recognition Method Based on a Lightweight Attention Network and Regularized Fine-Tuning},
journal = {Electronics},
year = {2025},
volume = {14},
number = {1},
pages = {211},
doi = {10.3390/electronics14010211}
}
EUVIMED