G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection

Abstract

Typical representations for arbitrary-oriented object detection tasks include oriented bounding box (OBB), quadrilateral bounding box (QBB), and point set (PointSet). Each representation encounters problems that correspond to its characteristics, such as the boundary discontinuity, square-like problem, representation ambiguity, and isolated points, which lead to inaccurate detection. Although many effective strategies have been proposed for various representations, there is still no unified solution. Current detection methods based on Gaussian modeling have demonstrated the possibility of breaking this dilemma; however, they remain limited to OBB. To go further, in this paper, we propose a unified Gaussian representation called G-Rep to construct Gaussian distributions for OBB, QBB, and PointSet, which achieves a unified solution to various representations and problems. Specifically, PointSet or QBB-based object representations are converted into Gaussian distributions, and their parameters are optimized using the maximum likelihood estimation algorithm. Then, three optional Gaussian metrics are explored to optimize the regression loss of the detector because of their excellent parameter optimization mechanisms. Furthermore, we also use Gaussian metrics for sampling to align label assignment and regression loss. Experimental results on several public available datasets, such as DOTA, HRSC2016, UCAS-AOD, and ICDAR2015, show the excellent performance of the proposed method for arbitrary-oriented object detection.

arXiv comment24 pages, 6 figures, 10 tables, the code has been open sourced at https://github.com/open-mmlab/mmrotate

References in corpus (14)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• UnitBox: An Advanced Object Detection Network
• Arbitrary-Oriented Scene Text Detection via Rotation Proposals
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
• A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
• SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
• RepPoints: Point Set Representation for Object Detection
• Few-shot Object Detection on Remote Sensing Images
• Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images

Cited by in corpus (2)

• MMRotate: A Rotated Object Detection Benchmark using PyTorch
• Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images