Asymmetrical Reverse Connection and Smooth-NMS for Object Detection
In this paper,we propose a new network structure,a more efficient object detection framework.Inspired by the original RON,we also joint the region-based and region-free methodologies of object detection.There is a lifting space in the accuracy of the original RON,so we design the following two structures:(a)design a new reverse connection structure,which can obtain much more information in small object detection;(b)design a new inception structure based on asymmetric convolution to improve the efficiency of object detectors.The conventional of non maximum suppression is replaced by more efficient Smooth-NMS in the object detection phase.With the use of low resolution 320 * 320 input size,the new network structure achieved 75.6%mAP(our method is 1.2%higher than the original RON)and 71.8%mAP on the standard PASCAL VOC 2007 and 2012 datasets respectively.The experimental results show that our method can generate higher detection accuracy.
Object detection Region proposal Convolutional neural network
Juan Peng Zhicheng Wang Xuan Lv Gang Wei Jingjing Fei Hongwei Zhang
Research Center of CAD,Tongji University,Shanghai,Peoples Republic of China Chongqing Land Resources Housing Surveying and Planning Institute,Chongqing 401121,China
国际会议
广州
英文
245-259
2018-11-23（万方平台首次上网日期，不代表论文的发表时间）