.png){kind=icon}
.png){kind=icon}
Return
Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
.png){kind=icon}
OA
AI
DOI：10.1109/LGRS.2021.3115110.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Arbitrary-oriented objects exist widely in remote sensing images. The mainstream rotation detectors use oriented bounding boxes (OBBs) or quadrilateral bounding boxes (QBBs) to represent the rotating objects. However, these methods suffer from the representation ambiguity for oriented object definition, which leads to suboptimal regression optimization and the inconsistency between the loss metric and the localization accuracy of the predictions. In this letter, we propose a representation invariance loss (RIL) to optimize the bounding box regression for the rotating objects in the remote sensing images. RIL treats multiple representations of an oriented object as multiple equivalent local minima and hence transforms bounding box regression into an adaptive matching process with these local minima. Next, the Hungarian matching algorithm is adopted to obtain the optimal regression strategy. Besides, we propose a normalized rotation loss to alleviate the weak correlation between different variables and their unbalanced loss contribution in OBB representation. Extensive experiments on remote sensing datasets show that our method achieves consistent and substantial improvement. The code and models are available at https://github.com/ming71/RIDet to facilitate future research.
Keywords:
Optimization
Object detection
Detectors
Training
Remote sensing
Transforms
Task analysis
Bounding box regression
convolutional neural networks
oriented object detection
representation ambiguity
Journal
IF:
16.4
Papers:
1.0W
Citations:
5.1K