Object detection usually adopts two-stage end-to-end networks, which use backbone network (such as VGG and ResNet) for feature extraction and are combined with the region proposal network (RPN) for object localization and classification. In this paper, we explore a novel depthwise grouped convolution (DGC) in the backbone network by integrating channels grouping and depthwise separable convolution, which is able to share the convolution parameters in different channels to reduce the amounts of parameters for speeding up training. In particular, split and shuffle strategies of channels are introduced to enhance information exchange between different groups of channels in DGC block, which can prevent the decrease of performance caused by insufficient object samples. Furthermore, non-local block is adopted in RPN to focus on small objects that are hard to identify. Consequently, we introduce margin-based loss to guide the model training together with the loss of classification and regression. Experiments conducted on the VOC2007, VOC2012 and COCO2017 datasets demonstrate the efficiency and effectiveness of our method for object detection.

目标检测通常采用两阶段端到端网络，使用骨干网络（如 VGG 和 ResNet）进行特征提取，并结合区域提议网络（RPN）进行目标定位和分类。在本文中，我们通过整合通道分组和深度可分离卷积，在骨干网络中探索了一种新颖的深度分组卷积（DGC），它能够共享不同通道中的卷积参数以减少参数数量以加快训练速度。特别是引入了通道的split和shuffle策略，增强了DGC块中不同通道组之间的信息交换，可以防止由于对象样本不足而导致的性能下降。此外，RPN 中采用 non-local block 来专注于难以识别的小对象。因此，我们引入了基于边际的损失来指导模型训练以及分类和回归的损失。在 VOC2007、VOC2012 和 COCO2017 数据集上进行的实验证明了我们的目标检测方法的效率和有效性。