4.7 Article

RSDet plus plus : Point-Based Modulated Loss for More Accurate Rotated Object Detection

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2022.3186070

关键词

Object detection; Detectors; Sensitivity; Feature extraction; Benchmark testing; Training; Measurement units; Rotated object detection; modulated loss; point-based; tiny objects

资金

  1. Commercialization of Research Findings Fund of Inner Mongolia Autonomous Region [2020CG0075]

向作者/读者索取更多资源

In this paper, we propose a novel method for detecting rotation sensitivity errors (RSE) by introducing a modulated rotation loss to mitigate performance degradation. The proposed method achieves competitive results in rotated object detection and effectively detects tiny objects.
We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration. We introduce a novel modulated rotation loss to alleviate the problem and a rotation sensitivity detection network (RSDet) which consists of an eight-param single-stage rotated object detector and the modulated rotation loss. Our proposed RSDet has several advantages: 1) it reformulates the rotated object detection problem as predicting the corners of objects while most previous methods employ a five-param-based regression method with different measurement units. 2) modulated rotation loss achieves consistent improvement on both five-param and eight-param rotated object detection methods by solving the discontinuity of loss. To further improve the accuracy of our method on objects smaller than 10 pixels, we introduce a novel RSDet++ which consists of a point-based anchor-free rotated object detector and a modulated rotation loss. Extensive experiments demonstrate the effectiveness of both RSDet and RSDet++, which achieve competitive results on rotated object detection in the challenging benchmarks DOTA-v1.0, DOTA-v1.5, and DOTA-v2.0. We hope the proposed method can provide a new perspective for designing algorithms to solve rotated object detection and pay more attention to tiny objects. The codes and models are available at: https://github.com/yangxue0827/RotationDetection.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据