Fake Logo Detection Using Deep Learning with AttentionBased Multi-Scale Feature Fusion
International Journal of AI Electrical Civil and Mechanical engineering · 25.03.2025 · 1 (1) · 163-173
DOI: 10.64751/m8mexs04 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of AI Electrical Civil and Mechanical engineering, online erschienen am 25.03.2025. Verfasst von Mr. N. Venkatesh und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Fake Logo Detection Using Deep Learning presents a fundamental challenge in Deep Learning, Brand Protection. Existing approaches, including SIFT+SVM, ORB+RF, and VGG16, process input data at a single resolution and fail to capture patterns spanning multiple scales, resulting in a mean accuracy ceiling on benchmark datasets. We address this limitation by introducing LogoGuard, a hybrid deep learning framework that integrates three parallel convolutional streams (kernel sizes 3, 7, and 13) with bidirectional LSTM encoding and a gated attention fusion module. We propose a parameter-sharing strategy within the attention mechanism that reduces trainable parameters while maintaining representational capacity. We train and evaluate our framework on FakeLogo-400, LOGO-Net using stratified 10-fold cross-validation. Our method achieves a mean precision (%) of 93.8% on the primary benchmark, surpassing the nearest baseline by 3.6 percentage points (p < 0.001, Cohen's d = 1.42). We further demonstrate a 28.4% reduction in computational cost relative to comparable hybrid architectures and convergence within 148 epochs on all benchmark datasets.
Zitieren
APA
Venkatesh, M. N., Goud, E. S., Aashrith, M., Shamshoddin, M., & Dushyanth, R. (2025). Fake Logo Detection Using Deep Learning with AttentionBased Multi-Scale Feature Fusion. International Journal of AI Electrical Civil and Mechanical engineering, 1(1), 163-173. https://doi.org/10.64751/m8mexs04
Vancouver
Venkatesh MN, Goud ES, Aashrith M, Shamshoddin M, Dushyanth R. Fake Logo Detection Using Deep Learning with AttentionBased Multi-Scale Feature Fusion. International Journal of AI Electrical Civil and Mechanical engineering. 2025;1(1):163-173. doi:10.64751/m8mexs04
BibTeX
@article{Venkatesh2025,
author = {Venkatesh, Mr. N. and Goud, Errola Shiva and Aashrith, Mariyala and Shamshoddin, Mohammad and Dushyanth, Reddypally},
title = {Fake Logo Detection Using Deep Learning with AttentionBased Multi-Scale Feature Fusion},
journal = {International Journal of AI Electrical Civil and Mechanical engineering},
year = {2025},
volume = {1},
number = {1},
pages = {163--173},
doi = {10.64751/m8mexs04}
}
EUVIMED