Research on Garbage Classification Algorithms Based on Attention Mechanisms and Deep Learning

With rapid urbanization and increasing population density, effective waste sorting has become crucial for environmental protection. The diverse nature of waste-varying in type, shape, and background-necessitates precise deep learning models. This study investigates the integration of various attention mechanisms at different positions within the YOLOv8 architecture to enhance waste sorting accuracy. We systematically assess the impact of these attention mechanisms and their specific placements on algorithm performance. Our experimental results not only demonstrate the effectiveness of attention mechanisms in improving mean Average Precision (mAP) but also identify the most effective attention mechanism modules and their optimal locations. Additionally, we propose future research directions, including refining attention mechanism integration strategies and expanding training datasets, to further improve the model's generalization and adaptability to a wider range of real-world scenarios.