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

TL;DR

The paper introduces EARL, a novel label assignment method for oriented object detection in remote sensing images, which adaptively selects high-quality samples considering target scales and shapes, improving detection accuracy.

Contribution

The paper proposes EARL, an adaptive label assignment framework utilizing elliptical distribution and scale sampling strategies to enhance remote sensing object detection performance.

Findings

Achieves state-of-the-art detection results on multiple datasets.

Effectively filters out low-quality samples, improving training efficiency.

Easily integrates with various detectors without additional modifications.

Abstract

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 multi-level 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 aided sampling (DED) 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.