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 300x300 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.
翻译:SDD(Singshot Moltipbox 探测器)是因其高精度和快速而最成功的物体探测器之一。然而,SDD的浅层(主要是Conv4_3)的特征缺乏语义信息,导致小物体的性能差。在本文中,我们提议DDSD(DisD(DisD(DisDL和Decvolution Slation Slation Socken Abox 探测器)),这是一个具有新颖特性的聚合模块,可以提高小型物体探测的性能。在特性组合模块中,DDSDSD用于扩大浅层和分流模块特征的接收范围,以增加高层地貌图的大小。我们的网络在PASCAL VOC2007 测试中实现了79.7%的MAP,在MS CO 测试-dev(MS CO) 41 FPS,只有300x300个输入,使用单个Nvidia 1080 GPU。对于小物体来说,DSDSD在MS CO 上达到10.5%,在FLIR热数据设置上达到22.8%,在速度和速度两方面都显示大量的状态的物体探测速度和速度。