Fake Logo Detection Using Deep Learning with AttentionBased Multi-Scale Feature Fusion

Abstract

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.