ASOD-Net: Arbitrary Sampling and Offset-based Detection Network for Remote Sensing Image
Liu, Xiwei
Liu, Xiwei
Author
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Remote sensing object detection plays a critical role in analyzing aerial imagery, enabling the accurate localization of arbitrarily oriented objects. Traditional detection frameworks often suffer from computational inefficiencies and feature misalignment due to the reliance on pre-defined rotated anchors and fixed convolutional sampling patterns. To address these limitations, we propose ASOD-Net, an Arbitrary Sampling and Offset-based Detection Network, which integrates Arbitrary Sampling Convolution (ASConv) and a differential offset-based bounding box representation. ASConv dynamically adjusts sampling positions to improve feature adaptability, while the offset-based bounding box representation enhances regression stability and reduces dependency on anchor angles. Extensive experiments on DOTA, HRSC2016, and UCAS-AOD demonstrate that our approach significantly improves detection accuracy, robustness, and computational efficiency.
Citation
X. Liu, "ASOD-Net: Arbitrary Sampling and Offset-based Detection Network for Remote Sensing Image," 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025, pp. 1-7, doi: 10.1109/IJCNN64981.2025.11227630
Source
Proceedings of the International Joint Conference on Neural Networks (IJCNN)
Conference
2025 International Joint Conference on Neural Networks, IJCNN 2025
Keywords
Arbitrary Sampling Convolution, Feature Alignment, Object Detection, Remote Sensing Image
Subjects
Source
2025 International Joint Conference on Neural Networks, IJCNN 2025
Publisher
IEEE