Object detection across different scales is challenging as the variances of object scales. Thus, a novel detection network, Top-Down Feature Fusion Single Shot MultiBox Detector (TDFSSD), is proposed. The proposed network is based on Single Shot MultiBox Detector (SSD) using VGG-16 as backbone with a novel, simple yet efficient feature fusion module, namely, the Top-Down Feature Fusion Module. The proposed module fuses features from higher-level features, containing semantic information, to lower-level features, containing boundary information, iteratively. Extensive experiments have been conducted on PASCAL VOC2007, PASCAL VOC2012, and MS COCO datasets to demonstrate the efficiency of the proposed method. The proposed TDFSSD network is trained end to end and outperforms the state-of-the-art methods across the three datasets. The TDFSSD network achieves 81.7% and 80.1% mAPs on VOC2007 and 2012 respectively, which outperforms the reported best results of both one-stage and two-stage frameworks. In the meantime, it achieves 33.4% mAP on MS COCO test-dev, especially 17.2% average precision (AP) on small objects. Thus all the results show the efficiency of the proposed method on object detection. Code and model are available at: https://github.com/dongfengxijian/TDFSSD.

随着对象比例的变化，跨不同比例的对象检测具有挑战性。因此，提出了一种新颖的检测网络，即自上而下的特征融合单发多盒检测器（TDFSSD）。拟议的网络基于以VGG-16为骨干的Single Shot MultiBox Detector（SSD），具有新颖，简单而有效的特征融合模块，即Top-Down特征融合模块。所提出的模块将包含语义信息的高级特征与包含边界信息的低级特征进行迭代地融合。已经对PASCAL VOC2007，PASCAL VOC2012和MS COCO数据集进行了广泛的实验，以证明该方法的有效性。所提议的TDFSSD网络经过了端到端的培训，并且在三个数据集中的性能均优于最新方法。TDFSSD网络在VOC2007和VOC 2007上分别实现了81.7％和80.1％的mAP，这优于报告的一阶段和两阶段框架的最佳结果。同时，在MS COCO测试开发中，它的mAP达到33.4％，特别是在小物体上的平均精度（AP）为17.2％。因此所有结果都表明了该方法在目标检测中的有效性。代码和模型可在以下网址获得：https：//github.com/dongfengxijian/TDFSSD。