Laser & Optoelectronics Progress, Volume. 57, Issue 6, 061008(2020)
Object Detection Algorithm Guided by Dual Attention Models
Figures & Tables(7)
Table 1. Comparison of detection results with different detection algorithms%
View tableTable 1. Comparison of detection results with different detection algorithms%
Method Backbone AP AP50 AP75 APS APM APL Faster R-CNN+++[ 8 ]ResNet-101-C4 34.9 55.7 37.4 15.6 38.7 50.9 Faster R-CNN (FR) by G-RMI[ 28 ]ResNet-101-C4 34.7 55.5 36.7 13.5 38.1 52.0 YOLOv2[ 24 ]DarkNet-19 21.6 44.0 19.2 5.0 22.4 35.5 SSD513[ 4 ]ResNet-101-SSD 31.2 50.4 33.3 10.2 34.5 49.8 DSSD513[ 26 ]ResNet-101-DSSD 33.2 53.3 35.2 13.0 35.4 51.1 RON[ 31 ]VGG-16 27.4 27.1 49.5 - - - DeNet[ 29 ]DeNet-101 33.8 53.4 36.1 12.3 36.1 50.8 CoupleNet[ 22 ]ResNet-101 33.1 53.5 35.4 11.6 36.3 50.1 YoLov3[ 25 ]DarkNet-53 33.0 57.9 34.4 18.3 35.4 41.9 SIN[ 23 ]VGG-16 23.2 44.5 22.0 7.3 24.5 36.3 Relation Network[ 32 ]ResNet-50 32.5 54.0 33.8 - - - MLKP[ 30 ]ResNet-101 26.9 48.4 26.9 8.6 29.2 41.1 MFCA (ours) ResNet-101 36.2 54.5 38.7 18.5 39.2 47.6
Table 2. Comparison of test results of each module%
View tableTable 2. Comparison of test results of each module%
Module Backbone AP AP50 AP75 APS APM APL Baseline ResNet-101 35.0 52.6 37.7 17.1 38.8 48.0 Baseline+MFCA ResNet-101 35.5 53.3 38.1 18.4 39.2 48.1 Baseline+MFCA+SCSA ResNet-101 35.9 54.0 38.6 18.8 39.8 48.5
Tools
Get Citation
Copy Citation Text
Zhong Ji, Qiankun Kong, Jian Wang. Object Detection Algorithm Guided by Dual Attention Models[J]. Laser & Optoelectronics Progress, 2020, 57(6): 061008
Paper Information
Category: Image Processing
Received: Jul. 10, 2019
Accepted: Aug. 28, 2019
Published Online: Mar. 6, 2020
The Author Email: Jian Wang (jianwang@tju.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20