Improving Object Detection With One Line of Code

论文地址：https://arxiv.org/abs/1704.04503

Github项目：https://github.com/bharatsingh430/soft-nms

Improving Object Detection With One Line of Code

Navaneeth Bodla,  Bharat Singh,  Rama Chellappa,  Larry S. Davis

(Submitted on 14 Apr 2017)

Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process. Soft-NMS obtains consistent improvements for the coco-style mAP metric on standard datasets like PASCAL VOC 2007 (1.7\% for both R-FCN and Faster-RCNN) and MS-COCO (1.3\% for R-FCN and 1.1\% for Faster-RCNN) by just changing the NMS algorithm without any additional hyper-parameters. Further, the computational complexity of Soft-NMS is the same as traditional NMS and hence it can be efficiently implemented. Since Soft-NMS does not require any extra training and is simple to implement, it can be easily integrated into any object detection pipeline. Code for Soft-NMS is publicly available on GitHub \url{ this http URL}.

Comments:	ICCV 2017 submission
Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:1704.04503 [cs.CV]
	(or arXiv:1704.04503v1 [cs.CV] for this version)