EARL: An Elliptical Distribution Aided Adaptive Rotation Label Assignment for Oriented Object Detection in Remote Sensing Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 61; pp. 1 - 15
• Main Authors: Guan, Jian, Xie, Mingjie, Lin, Youtian, He, Guangjun, Feng, Pengming
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive sampling; Adaptive scale sampling; anchor-free detector; Aspect ratio; Detection; Detectors; Distance; Distribution; elliptical distribution; Feature extraction; Feature maps; label assignment; Labels; Object detection; Object recognition; Proposals; Remote sensing; remote sensing images (RSIs); Rotation; Sampling; Shape; Source code; Training; Weighting
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2023.3311416

Label assignment is a crucial process in object detection, which significantly influences the detection performance by determining positive or negative samples during training process. However, existing label assignment strategies barely consider the characteristics of targets in remote sensing images (RSIs) thoroughly, e.g., large variations in scales and aspect ratios, leading to insufficient and imbalanced sampling and introducing more low-quality samples, thereby limiting detection performance. To solve the above problems, an elliptical distribution aided adaptive rotation label assignment (EARL) is proposed to select high-quality positive samples adaptively in anchor-free detectors. Specifically, an adaptive scale sampling (ADS) strategy is presented to select samples adaptively among multilevel feature maps according to the scales of targets, which achieves sufficient sampling with more balanced scale-level sample distribution. In addition, a dynamic elliptical distribution (DED) aided sampling strategy is proposed to make the sample distribution more flexible to fit the shapes and orientations of targets and filter out low-quality samples. Furthermore, a spatial distance weighting (SDW) module is introduced to integrate the adaptive distance weighting into loss function, which makes the detector more focused on the high-quality samples. Extensive experiments on several popular datasets demonstrate the effectiveness and superiority of our proposed EARL, where without bells and whistles it can be easily applied to different detectors and achieve state-of-the-art performance. The source code will be available at: https://github.com/Justlovesmile/EARL .