Heterogeneous attention fusion network with multi-branch decoding for UAV semantic segmentation
Journal of King Saud University Computer and Information Sciences · 2026-08 · 38 (6)
DOI: 10.1007/s44443-026-00757-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 20.04.2026. Verfasst von Sai Li und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Shandong Provincial Natural Science Foundation.
Abstract (Originalsprache)
Semantic segmentation of Unmanned Aerial Vehicle (UAV) imagery remains a formidable task owing to extreme scale variation, cluttered backgrounds, and oblique viewing geometry. Existing approaches suffer from three interrelated limitations: (i) single-attention architectures employ only one attention paradigm throughout the decoder, inherently restricting the network to either global context or fine-grained local detail but not both; (ii) homogeneous multi-branch designs replicate the same attention type across branches, which increases computation without introducing representational diversity; and (iii) prevailing feature fusion strategies—element-wise addition and concatenation—lack channel-level adaptivity, failing to exploit the complementary strengths of heterogeneous feature sources. To overcome this bottleneck, we propose HAFNet (Heterogeneous Attention Fusion Network), which introduces a multi-branch decoder in which four parallel branches—employing multi-head, spatial, self-, and shifted-window attention, respectively—decode shared encoder features concurrently. A squeeze-and-excitation (SE) enhanced aggregation module then adaptively recalibrates and fuses the branch outputs at the channel level, enabling the network to leverage the complementary strengths of diverse attention mechanisms within a single forward pass. Extensive experiments on four public benchmarks demonstrate that HAFNet establishes new state-of-the-art results, achieving 72.1% mIoU on UAVid, 84.5% on ISPRS Vaihingen, 88.2% on ISPRS Potsdam, and 54.8% on LoveDA, surpassing the latest competing methods including UrbanSSF-L and UNetFormer. Ablation studies further verify that each branch provides unique and complementary representations; the full four-branch configuration consistently outperforms every subset, yielding especially pronounced improvements on small-scale objects (+18.3% F1 for cars) and heterogeneous land-cover categories.
Förderung
- Shandong Provincial Natural Science Foundation
Zitieren
APA
Li, S., & Huang, S. (2026). Heterogeneous attention fusion network with multi-branch decoding for UAV semantic segmentation. Journal of King Saud University Computer and Information Sciences, 38(6). https://doi.org/10.1007/s44443-026-00757-9
Vancouver
Li S, Huang S. Heterogeneous attention fusion network with multi-branch decoding for UAV semantic segmentation. Journal of King Saud University Computer and Information Sciences. 2026;38(6). doi:10.1007/s44443-026-00757-9
BibTeX
@article{Li2026,
author = {Li, Sai and Huang, Shuo},
title = {Heterogeneous attention fusion network with multi-branch decoding for UAV semantic segmentation},
journal = {Journal of King Saud University Computer and Information Sciences},
year = {2026},
volume = {38},
number = {6},
doi = {10.1007/s44443-026-00757-9}
}
EUVIMED