DMAC-YOLO: A High-Precision YOLO v5s Object Detection Model

• 1、School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876

Abstract：YOLO v5s is one of the commonly used one-stage object detection algorithms currently, known for its small size and fast speed. However, its main limitation is its lower accuracy. To address this issue, this paper proposes an improved YOLO v5s model, DMAC-YOLO, which introduces the AdamPlus optimizer as an improvement to the Adam optimizer, for higher accuracy and faster convergence compared to traditional optimizers. The model employs the Decoupled Head approach to improve gradient propagation during training and incorporates the SIoU Loss function to reduce false positives and missed detections. Additionally, by enhancing the original network structure of YOLO v5s and incorporating the CBAM attention mechanism, the model\'s feature extraction capabilities are improved. Experiments show that compared to the YOLO v5s model, the DMAC-YOLO model increases mAP@0.5 by 6.0% to 84.3% and mAP@0.95 by 13.2% to 64.2% on the PASCAL VOC dataset. On the COCO dataset, the DMAC-YOLO model\'s mAP@0.5 is improved by 4.0% to 56.7%, and mAP@0.95 by 4.2% to 37.4%. Moreover, ablation experiments demonstrate that the proposed improvements enable the model to converge quickly while maintaining a balance between accuracy and speed.

Keywords： Object detection Optimizer Decoupled head Loss function Attention mechanisms