MS-CADNet: A Multi-Scale Context Attention Network for Efficient Object Detection in UAV Imagery
ICCK Transactions on Sensing, Communication, and Control · 23.04.2026 · 3 (2) · 64-75
DOI: 10.62762/tscc.2026.214827 ↗Kurz gefasst
Fachartikel in der Zeitschrift ICCK Transactions on Sensing, Communication, and Control, online erschienen am 23.04.2026. Verfasst von Abdul Bari und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
With the rapid advancement of unmanned aerial vehicle (UAV) technology, there is a need for lightweight and accurate object detection on resource-constrained platforms. This paper proposes MS-CADNet, an anchor-free network for small object detection in aerial imagery. It uses a MobileNetV3-Small backbone and a two-branch gated Context Attention Module (CAM) to enhance feature quality. On the VisDrone-DET benchmark, it achieves 31.2% mAP, surpassing YOLOv8-Small and CEASC. The model attains 19.2% AP for small objects with only 3.1M parameters and 5.4 GFLOPs, making it suitable for real-time UAV deployment.
Zitieren
APA
Bari, A., Memon, F., Waheed, H., & Abro, G. E. M. (2026). MS-CADNet: A Multi-Scale Context Attention Network for Efficient Object Detection in UAV Imagery. ICCK Transactions on Sensing, Communication, and Control, 3(2), 64-75. https://doi.org/10.62762/tscc.2026.214827
Vancouver
Bari A, Memon F, Waheed H, Abro GEM. MS-CADNet: A Multi-Scale Context Attention Network for Efficient Object Detection in UAV Imagery. ICCK Transactions on Sensing, Communication, and Control. 2026;3(2):64-75. doi:10.62762/tscc.2026.214827
BibTeX
@article{Bari2026,
author = {Bari, Abdul and Memon, Fatima and Waheed, Hafsa and Abro, Ghulam E Mustafa},
title = {MS-CADNet: A Multi-Scale Context Attention Network for Efficient Object Detection in UAV Imagery},
journal = {ICCK Transactions on Sensing, Communication, and Control},
year = {2026},
volume = {3},
number = {2},
pages = {64--75},
doi = {10.62762/tscc.2026.214827}
}
EUVIMED