DAS-Net: A Lightweight Dynamic Convolution Network with Attention Gates and Deep Supervision for UAV Semantic Segmentation
Applied Sciences · 05.06.2026 · 16 (11) · 5688
DOI: 10.3390/app16115688 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 05.06.2026. Verfasst von Young Jae Kim und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Research Institute for Defense Technology Planning and Advancement.
Abstract (Originalsprache)
Anti-UAV surveillance demands real-time pixel-level UAV localization on resource-constrained gimbal-mounted platforms, yet existing lightweight segmentation models suffer from low recall that propagates to downstream tracking failure. Building on our prior dataset of 605,045 paired visible-light and infrared images, we extend the lightweight ThinDyUNet baseline with three architectural improvements: (1) symmetric dynamic convolution applied to both the encoder and decoder, (2) attention gates filtering skip connections, and (3) deep supervision with auxiliary loss heads. The resulting DAS-Net is evaluated under a three-seed Monte Carlo cross-validation protocol on the full 174,008-image test set. DAS-Net achieves a mean test mIoU of 0.6780 and Dice coefficient of 0.7509 across three independent seeds, outperforming the ThinDyUNet baseline by +6.65 percentage points (pp) in mIoU with statistical significance (one-sided paired t-test, p = 0.045, Cohen’s d = 1.74; full variance and significance analysis in the experimental section). DAS-Net matches the best-performing external baseline (UNet) and exceeds the others (MobileUNet, PAN, PSPNet) while using approximately 14.7× fewer parameters than ResNet-34-based variants. DAS-Net runs at 8.83 ms per image on an NVIDIA A6000 GPU (113 FPS) and 38.44 ms on an NVIDIA Jetson AGX Orin (26 FPS at FP16), demonstrating real-time deployability across server-class and embedded edge platforms.
Förderung
- Korea Research Institute for Defense Technology Planning and Advancement
Zitieren
APA
Kim, Y. J., & Kim, S. (2026). DAS-Net: A Lightweight Dynamic Convolution Network with Attention Gates and Deep Supervision for UAV Semantic Segmentation. Applied Sciences, 16(11), 5688. https://doi.org/10.3390/app16115688
Vancouver
Kim YJ, Kim S. DAS-Net: A Lightweight Dynamic Convolution Network with Attention Gates and Deep Supervision for UAV Semantic Segmentation. Applied Sciences. 2026;16(11):5688. doi:10.3390/app16115688
BibTeX
@article{Kim2026,
author = {Kim, Young Jae and Kim, Sang-Chul},
title = {DAS-Net: A Lightweight Dynamic Convolution Network with Attention Gates and Deep Supervision for UAV Semantic Segmentation},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {11},
pages = {5688},
doi = {10.3390/app16115688}
}
EUVIMED