SADFF-Net: Scale-Aware Detection and Feature Fusion for Multiscale Remote Sensing Object Detection
- 5 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Abstract
Multi-scale object detection in remote sensing imagery poses significant challenges, including substantial variations in object size, diverse orientations, and interference from complex backgrounds. To address these issues, we propose SADFF-Net, a novel detection framework that incorporates a Multi-scale Contextual Attention Fusion (MCAF) module to enhance information exchange between feature layers and suppress irrelevant feature interference. In addition, SADFF-Net employs an Adaptive Spatial Feature Fusion (ASFF) module to improve semantic consistency across feature layers by assigning spatial weights at multiple scales. To enhance adaptability to scale variations, the regression head integrates a deformable convolution. In contrast, the classification head utilizes depth-wise separable convolutions to significantly reduce computational complexity without compromising detection accuracy. Extensive experiments on the DOTAv1 and DIOR_R datasets demonstrate that SADFF-Net outperforms current state-of-the-art methods in multi-scale object detection.Keywords
Funding Information
- Youth Project of the Applied Basic Research Program of Shanxi Province (202203021222027)
This publication has 17 references indexed in Scilit:
- Context in object detection: a systematic literature reviewArtificial Intelligence Review, 2025
- Brain-Inspired Online Adaptation for Remote Sensing With Spiking Neural NetworkIEEE Transactions on Geoscience and Remote Sensing, 2025
- Surveying You Only Look Once (YOLO) Multispectral Object Detection Advancements, Applications, and ChallengesIEEE Access, 2025
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection2024
- Probabilistic Intersection-Over-Union for Training and Evaluation of Oriented Object DetectorsIEEE Transactions on Image Processing, 2024
- Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection2023
- Oriented RepPoints for Aerial Object Detection2022
- OSKDet: Orientation-sensitive Keypoint Localization for Rotated Object Detection2022
- ACE: Anchor-Free Corner Evolution for Real-Time Arbitrarily-Oriented Object DetectionIEEE Transactions on Image Processing, 2022
- Deformable ConvNets V2: More Deformable, Better Results2019