Single shot multibox detector (SSD) takes several feature layers for object detection, but each layer is used independently. This structure may ignore some context information and is not conducive to improving the detection accuracy of small objects. Moreover, the imbalances of samples and multi-tasks during SSD training process can lead to inefficient training and model degradation. In order to improve the performance of SSD, this paper proposes a balanced feature fusion SSD (BFSSD) algorithm. Firstly, a feature fusion module is proposed to fuse and refine different layers of the feature pyramid. Then, a more balanced L1 loss function is proposed to further solve these imbalances. Finally, our model is trained with Pascal VOC2007 and VOC2012 trainval datasets and tested on Pascal VOC2007 test datasets. Simulation results show that, for the input size of 300 × 300, BFSSD exceeds the best results provided by the conventional SSD and other advanced object detection algorithms.

中文翻译：

---

用于物体检测的平衡功能融合SSD

单发多盒检测器（SSD）需要几个特征层来进行对象检测，但是每个层都是独立使用的。这种结构可能会忽略一些上下文信息，并且不利于提高小物体的检测精度。而且，SSD训练过程中样本和多任务的不平衡会导致训练效率低下和模型退化。为了提高SSD的性能，提出了一种平衡特征融合SSD（BFSSD）算法。首先，提出了一种特征融合模块，以融合和完善特征金字塔的不同层。然后，提出了更平衡的L1损失函数来进一步解决这些不平衡问题。最后，我们的模型使用Pascal VOC2007和VOC2012训练数据集进行训练，并在Pascal VOC2007测试数据集上进行了测试。仿真结果表明，