Enhancing Real-Time Semantic Segmentation With Routing Attention and Boundary-Guided Fusion
IEEE Signal Processing Letters · 2026 · 33 · 4321-4325
DOI: 10.1109/lsp.2026.3746925 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Jiaxuan Kang und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben.
Abstract (Originalsprache)
Real-time semantic segmentation requires accurate prediction under strict latency constraints. Existing CNN-Transformer dual-branch methods combine a high-resolution CNN branch for spatial details with a low-resolution Transformer branch for semantic context, but they still suffer from limited context coverage in efficient attention and unreliable cross-branch fusion caused by feature-space inconsistency and spatial misalignment. We propose RBNet, a real-time semantic segmentation network with two novel designs for efficient attention and cross-branch feature fusion. To improve efficient contextual modeling, we introduce Head-wise Bi-Level Routing Attention, which enables each attention head to adaptively select relevant regions and aggregate more diverse context. To improve cross-branch interaction, we design an Alignment and Boundary-Guided Fusion module with Boundary Guidance and Interior Suppression loss to align CNN and Transformer features, correct spatial misalignment, and learn boundary-aware gates for reliable fusion. Experiments on Cityscapes and CamVid demonstrate that RBNet achieves a favorable balance between segmentation accuracy and inference speed.
Zitieren
APA
Kang, J., Li, S., Tang, X., Mu, Y., & Xiang, W. (2026). Enhancing Real-Time Semantic Segmentation With Routing Attention and Boundary-Guided Fusion. IEEE Signal Processing Letters, 33, 4321-4325. https://doi.org/10.1109/lsp.2026.3746925
Vancouver
Kang J, Li S, Tang X, Mu Y, Xiang W. Enhancing Real-Time Semantic Segmentation With Routing Attention and Boundary-Guided Fusion. IEEE Signal Processing Letters. 2026;33:4321-4325. doi:10.1109/lsp.2026.3746925
BibTeX
@article{Kang2026,
author = {Kang, Jiaxuan and Li, Sumei and Tang, Xinyi and Mu, Yufan and Xiang, Wei},
title = {Enhancing Real-Time Semantic Segmentation With Routing Attention and Boundary-Guided Fusion},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {4321--4325},
doi = {10.1109/lsp.2026.3746925}
}
EUVIMED