Improvement and Enhancement of YOLOv5 Small Target Recognition Based on Multi-module Optimization
This provides an incremental optimization strategy for YOLOv5s in small target detection, benefiting researchers and practitioners in computer vision applications.
The paper tackled the limitations of YOLOv5s in small target detection by introducing multi-module optimizations, resulting in enhanced precision, recall, and mAP, with significant improvements in complex backgrounds and tiny targets in real-world tests.
In this paper, the limitations of YOLOv5s model on small target detection task are deeply studied and improved. The performance of the model is successfully enhanced by introducing GhostNet-based convolutional module, RepGFPN-based Neck module optimization, CA and Transformer's attention mechanism, and loss function improvement using NWD. The experimental results validate the positive impact of these improvement strategies on model precision, recall and mAP. In particular, the improved model shows significant superiority in dealing with complex backgrounds and tiny targets in real-world application tests. This study provides an effective optimization strategy for the YOLOv5s model on small target detection, and lays a solid foundation for future related research and applications.