YOLO-DAW:基于窗口内部双重注意力机制的目标检测模型  

YOLO-DAW:Object detection model based on dual attention mechanism within windows

作　　者：殷智伟 邵家玉 张宁[1,2] Yin Zhiwei;Shao Jiayu;Zhang Ning(Key Laboratory of Measurement and Control of Complex Systems of Ministry of Education,Southeast University,Nanjing 210096,China;Intelligent Transportation System Research Center of Ministry of Education,Southeast University,Nanjing 211189,China)

机构地区：[1]东南大学复杂工程系统测量与控制教育部重点实验室,南京210096 [2]东南大学教育部智能运输系统研究中心,南京211189

出　　处：《东南大学学报（自然科学版）》2023年第4期718-724,共7页Journal of Southeast University：Natural Science Edition

摘　　要：为了将注意力机制引入YOLO模型,从而提高算法的特征融合能力和检测准确率,提出一种基于窗口内部双重注意力机制改进的YOLOv5模型(YOLO-DAW).在neck层中,模型在特征金字塔网络和路径聚合网络中进行特征融合时,分别引入通道注意力和空间注意力机制,并将注意力机制的计算限制在不同大小的窗口内,以降低模型的计算复杂度.不同性质的注意力机制能够为前向特征提供更大感受野的全局特征信息,极大加强了模型对不同特征的理解能力.实验结果表明:模型在公开数据集PASCAL VOC2012以及SODA10M上的mAP50分别达到了68.6%和51.9%;对比同参数量的YOLOv5m,YOLO-DAW在PASCAL VOC2012和SODA10M上均有1.2%的领先.改进后的模型能够更好地融合局部特征与全局特征,使其满足更复杂场景下的检测要求.To introduce the attention mechanism into the you only look once(YOLO)model,thereby improving the feature fusion ability and detection accuracy of the algorithm,an improved YOLOv5 model(YOLO-DAW)based on the dual attention mechanism inside the window is proposed.In the neck layer,when the model performs feature fusion in the feature pyramid network and path aggregation network,channel attention and spatial attention mechanisms are introduced respectively,and the calculation of the attention mechanism is limited to windows of different sizes to reduce computational complexity.Attention mechanisms of different nature can provide global feature information with a larger receptive field for forward features,which greatly enhances the model's ability to understand different features.Experimental results show that the mAP50 of the model on the public dataset PASCAL VOC2012 and SODA10M reaches 68.6%and 51.9%,respectively.Compared with YOLOv5m with the similar parameters,YOLO-DAW has a 1.2%lead in both PASCAL VOC2012 and SODA10M.The improved model can better integrate local features and global features,making it meet the detection requirements in more complex scenes.

关 键 词：目标检测 注意力机制 特征融合 基于全连接层的上采样 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]