基于YOLOx残差块融合CoA模块的改进检测网络

YOLOx-Darknet53是以YOLOv3为基准增加各种技巧(trick)升级改进的检测网络,但其仍然是以Darknet53为特征提取骨干网络(backbone),因此网络的特征提取能力仍有欠缺.本文依据CoTNet中的注意力机制改进得到CoA (contextual attention)模块,并将其替代YOLOx骨干网络残差块里的3×3卷积,得到融合注意力后的新残差块,加强了骨干网络的特征提取能力,并在Pascal VOC2007数据集上进行对比实验,融合CoA模块的网络比原网络的平均精度均值AP@.5:.95]高1.4, AP@0.5高1.4;在改进骨干网络后的YOLOx检测头前加入无参3D注意力模块,得到最终改进的检测网络,进行上述对比实验,结果表明比原网络的AP@.5:.95]高1.6,AP@0.5高1.5.因此,改进后的网络比原网络检测更加精准,在工业应用中能达到更好的检测效果.

Improved Detection Network Based on YOLOx Residual Block Fusion CoA Module

YOLOx-Darknet53 is an improved detection network integrating a basis of you only look once version 3 (YOLOv3) with various tricks added. Nevertheless, it still uses Darknet53 as the backbone network to extract features, so the feature extraction capability of the network is still insufficient. In this study, we acquire a contextual attention (CoA) module by improving the attention mechanism in CoTNet and replace the 3×3 convolution in the residual block of the YOLOx backbone network with the module to obtain a new residual block after attention fusion and thereby strengthen the feature extraction capability of the backbone network. A comparison experiment is conducted on the Pascal VOC2007 data set. The mean average precision AP@.5:.95] and the AP@0.5 of the network integrating the CoA module are both 1.4 higher than those of the original network. After the backbone network is improved, a non-parameter 3D attention module is added in front of the YOLOx detection head to obtain the final improved detection network. The results of another round of the above comparative experiment show that the AP@.5:.95] and the AP@0.5 of the final network are respectively 1.6 and 1.5 higher than those of the original network. Therefore, the improved network is more accurate than the original network in detection and can achieve better detection effects in industrial applications.