针对目标检测与图像分类任务的差别,以及大多数目标检测器过于依赖分类基础网络的问题,提出一种针对目标检测任务的基础网络。该网络包含初始模块、特征融合模块和混合下采样模块。初始模块能减少输入图片信息的丢失;特征融合模块通过拼接不同卷积层的输出,既能加强网络对不同尺寸目标检测的稳健性,又能对物体检测提供更多的上下文信息,有效提高了检测精确度;在网络的下采样部分引入混合下采样模块,平衡了基础网络对目标的分类和定位能力。实验结果表明,本网络模型在PASCAL VOC 2007和 PASCAL VOC 2012数据集上进行训练后,在PASCAL VOC 2007测试集上的平均精度均值可达81.0%,检测速度可达85 frame/s,本网络在精度和效率上都达到了很好的效果。

This paper proposes a backbone network for object detection aiming at the difference between object detection and image classification, to solve the problem that most object detectors are excessively dependent on the classification network. The network mainly includes the initial block, feature fusion module, and mix down-sampling module. The initial block can reduce information loss of the input image. By concatenating the outputs of different convolution layers, the feature fusion module not only enhances the robustness of the network to detection objects with various sizes but also provides more context information for object detection, which effectively improves detection accuracy. In the down-sampling part of the network, a mix down-sampling module is introduced, which balances the ability of the backbone network to classify and locate objects. Experimental results show that the mean value of average precision of the proposed model can reach 81.0% on the PASCAL VOC 2007 test set after training on PASCAL VOC 2007 and PASCAL VOC 2012 datasets, and the detection speed of the model is 85 frame/s, which ensures good performance in terms of accuracy and efficiency.