Dual Class Token Vision Transformer for Direction of Arrival Estimation in Low SNR
IEEE Signal Processing Letters · 2024 · 31 · 76-80
DOI: 10.1109/lsp.2023.3342628 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2024. Verfasst von Yu Guo und 2 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 21 Literaturangaben. Gefördert von: Key R&D Program of Shandong Province, Beijing Municipal Science and Technology Project.
Abstract (Originalsprache)
In this letter, we propose a deep learning-based method for the direction of arrival (DOA) estimation in the low signal-to-noise ratio (SNR) scenario. Specifically, the DOA estimation is modeled as a multi-label classification task, and a novel dual class token Vision Transformer (DCT-ViT) is designed to fit it. Different from the classical ViT architecture with a single class token, the DCT-ViT includes two class tokens which are located at the beginning and end of the latent vector sequence, respectively. This architecture enables enhanced information mining and feature extraction from the array signal data in order to improve the accuracy of DOA estimation. Furthermore, a single DCT-ViT model can accommodate different source numbers by leveraging a training dataset with different numbers of sources. Simulation results illustrate that our proposed method outperforms existing methods in the low SNR scenario, including classical model-based and other deep learning-based methods.
Förderung
- Key R&D Program of Shandong Province
- Beijing Municipal Science and Technology Project
Zitieren
APA
Guo, Y., Zhang, Z., & Huang, Y. (2024). Dual Class Token Vision Transformer for Direction of Arrival Estimation in Low SNR. IEEE Signal Processing Letters, 31, 76-80. https://doi.org/10.1109/lsp.2023.3342628
Vancouver
Guo Y, Zhang Z, Huang Y. Dual Class Token Vision Transformer for Direction of Arrival Estimation in Low SNR. IEEE Signal Processing Letters. 2024;31:76-80. doi:10.1109/lsp.2023.3342628
BibTeX
@article{Guo2024,
author = {Guo, Yu and Zhang, Zhi and Huang, Yuzhen},
title = {Dual Class Token Vision Transformer for Direction of Arrival Estimation in Low SNR},
journal = {IEEE Signal Processing Letters},
year = {2024},
volume = {31},
pages = {76--80},
doi = {10.1109/lsp.2023.3342628}
}
EUVIMED