R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
share
Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them accurately and quickly from the background. Though considerable progress has been made, there still exist challenges for rotating objects with large aspect ratio, dense distribution and category extremely imbalance. In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate positioning objects. Considering the shortcoming of feature misalignment in the current refined single-stage detector, we design a feature refinement module to improve detection performance, which is especially effective in the long tail data set. The key idea of feature refinement module is to re-encode the position information of the current refined bounding box to the corresponding feature points through feature interpolation to realize feature reconstruction and alignment. Extensive experiments on two remote sensing public datasets DOTA, HRSC2016 as well as scene text data ICDAR2015 show the state-of-the-art accuracy and speed of our detector. Source code and the models will be made public available upon the publish of the paper.
READ FULL TEXT
