跳跃式监视
最小边界框
高斯分布
间断(语言学)
边界(拓扑)
计算机科学
算法
公制(单位)
瓶颈
目标检测
回归
分割
数学
人工智能
数学优化
数学分析
统计
物理
图像(数学)
经济
嵌入式系统
量子力学
运营管理
作者
Xue Yang,Junchi Yan,Qi Ming,Wentao Wang,xiaopeng zhang,Qi Tian
出处
期刊:Cornell University - arXiv
日期:2021-01-01
被引量:55
标识
DOI:10.48550/arxiv.2101.11952
摘要
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even there is no overlapping between two rotating bounding boxes which is often the case for small object detection. Thanks to its three unique properties, GWD can also elegantly solve the boundary discontinuity and square-like problem regardless how the bounding box is defined. Experiments on five datasets using different detectors show the effectiveness of our approach. Codes are available at https://github.com/yangxue0827/RotationDetection and https://github.com/open-mmlab/mmrotate.
科研通智能强力驱动
Strongly Powered by AbleSci AI