Abstract | ||
---|---|---|
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. |
Year | Venue | Field |
---|---|---|
2018 | PRCV | Reverse connection,Object detection,Convolutional neural network,Convolution,Computer science,Algorithm,Non maximum suppression,Detector,Network structure |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
12 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Juan Peng | 1 | 1 | 0.70 |
Zhicheng Wang | 2 | 176 | 17.00 |
Xuan Lv | 3 | 3 | 1.41 |
Gang Wei | 4 | 0 | 0.34 |
Jingjing Fei | 5 | 0 | 1.35 |
Hongwei Zhang | 6 | 3 | 3.54 |