SSD (Single Shot MultiBox Detector) is one of the best object detection algorithms and is able to provide high accurate object detection performance in real time. However, SSD shows relatively poor performance on small object detection because its shallow prediction layer, which is responsible for detecting small objects, lacks enough semantic information. To overcome this problem, SKIPSSD, an improved SSD with a novel skip connection of multiscale feature maps, is proposed in this paper to enhance the semantic information and the details of the prediction layers through skippingly fusing high-level and low-level feature maps. For the detail of the fusion methods, we design two feature fusion modules and multiple fusion strategies to improve the SSD detector’s sensitivity and perception ability. Experimental results on the PASCAL VOC2007 test set demonstrate that SKIPSSD significantly improves the detection performance and outperforms lots of state-of-the-art object detectors. With an input size of 300 × 300, SKIPSSD achieves 79.0% mAP (mean average precision) at 38.7 FPS (frame per second) on a single 1080 GPU, 1.8% higher than the mAP of SSD while still keeping the real-time detection speed.

中文翻译：

---

一种通过跳过多尺度特征图改善SSD的方法。

SSD（单发MultiBox检测器）是最好的目标检测算法之一，能够实时提供高精度的目标检测性能。但是，SSD在小对象检测方面显示相对较差的性能，因为负责检测小对象的浅层预测层缺少足够的语义信息。为了克服这个问题，本文提出了一种具有新颖的多尺度特征图跳过连接的改进型固态硬盘SKIPSSD，通过将高级和低级特征图进行跳过来增强语义信息和预测层的细节。对于融合方法的细节，我们设计了两个功能融合模块和多种融合策略，以提高SSD检测器的灵敏度和感知能力。PASCAL VOC2007测试仪上的实验结果表明，SKIPSSD显着提高了检测性能，并且胜过了许多最新的物体检测器。SKIPSSD的输入大小为300×300，在单个1080 GPU上以38.7 FPS（每秒帧）的速度达到79.0％的mAP（平均精度），比SSD的mAP高1.8％，同时仍保持实时检测速度。