IoU-Adaptive Deformable R-CNN: Make Full Use of IoU for Multi-Class Object Detection in Remote Sensing Imagery

IoU-Adaptive Deformable R-CNN: Make Full Use of IoU for Multi-Class Object Detection in Remote Sensing Imagery

Recently, methods based on Faster region-based convolutional neural network (R-CNN) have been popular in multi-class object detection in remote sensing images due to their outstanding detection performance. The methods generally propose candidate region of interests (ROIs) through a region propose n...

Full description

Bibliographic Details
Main Authors: Jiangqiao Yan, Hongqi Wang, Menglong Yan, Wenhui Diao, Xian Sun, Hao Li
Format: Article
Language:English
Published: MDPI AG 2019-02-01
Series:Remote Sensing
Subjects:
remote sensing imagery
anchor matching
Cascade R-CNN
IoU-based weighted loss
non-maximum suppression
Online Access:https://www.mdpi.com/2072-4292/11/3/286

Internet

https://www.mdpi.com/2072-4292/11/3/286

Similar Items