AdVision: An efficient and effective deep learning based advertisement detector for printed media

Automated advertisement detection in newspapers is a challenging task due to the diversity in print layouts, formats, and design styles. This task has critical applications in media monitoring, content analysis, and advertising analytics. To address these challenges, we introduce AdVision, a deep-learning-based solution that treats advertisements as unique visual objects. We provide a comparative study of various detection architectures, including one-stage, two-stage, and transformer-based detectors, to identify the most effective approach for detecting advertisements. Our results are validated through extensive experiments conducted under different conditions and metrics. Newspapers from four different countries—Denmark, Norway, Sweden, and the UK—were selected to demonstrate the variety of languages and print formats. Additionally, we conduct a cross-analysis to show how training on one language can generalize to another. To enhance the explainability of our results, we employ GradCAM++ (Chattopadhay et al., 2018) heatmaps. Our experiments demonstrate that the YOLOv8 model achieves superior performance, balancing high precision and recall with minimal inference latency, making it particularly suitable for high-throughput advertisement detection. • Comprehensive evaluation of deep learning models on diverse newspaper datasets. • YOLOv8 outperforms other models in real-time Ad detection in printed media. • YOLOv8 struggles with unseen newspaper formats, indicating generalization limits. • Color and layout variations significantly impact YOLOv8’s detection accuracy. • Positional changes of Ads affect the YOLOv8’s detection capability.