Abstract

SSD (Single Shot Multibox Detector) is one of the most successful object detectors for its high accuracy and fast speed. However, the features from shallow layer (mainly Conv4_3) of SSD lack semantic information, resulting in poor performance in small objects. In this paper, we proposed DDSSD (Dilation and Deconvolution Single Shot Multibox Detector), an enhanced SSD with a novel feature fusion module which can improve the performance over SSD for small object detection. In the feature fusion module, dilation convolution module is utilized to enlarge the receptive field of features from shallow layer and deconvolution module is adopted to increase the size of feature maps from high layer. Our network achieves 79.7% mAP on PASCAL VOC2007 test and 28.3% mmAP on MS COCO test-dev at 41 FPS with only 300 × 300 input using a single Nvidia 1080 GPU. Especially, for small objects, DDSSD achieves 10.5% on MS COCO and 22.8% on FLIR thermal dataset, outperforming a lot of state-of-the-art object detection algorithms in both aspects of accuracy and speed.

中文翻译：

---

使用单发检测器检测热图像中的小物体

摘要

SSD（单发多盒检测器）以其高精度和高速度而成为最成功的对象检测器之一。但是，SSD的浅层（主要是Conv4_3）的功能缺少语义信息，从而导致小型对象的性能较差。在本文中，我们提出了DDSSD（扩张和解卷积单发多盒检测器），它是一种具有新型特征融合模块的增强型SSD，可以提高SSD在小物体检测方面的性能。在特征融合模块中，利用扩张卷积模块扩大了浅层特征的接收场，并采用了反卷积模块增大了高层特征图的大小。我们的网络使用单个Nvidia 1080 GPU仅以300×300的输入，在PASCAL VOC2007测试中达到了79.7％的mAP，在MS COCO测试开发中达到了28.3％的mmAP，输入速度仅为300×300。