Accurate channel estimation is critical for high-performance Orthogonal Frequency-Division Multiplexing systems such as 5G New Radio, particularly under low signal-to-noise ratio and stringent latency constraints. This letter presents HELENA, a compact deep learning model that combines a lightweight convolutional backbone with two efficient attention mechanisms: patch-wise multi-head self-attention for capturing global dependencies and a squeeze-and-excitation block for local feature refinement. Compared to CEViT, a state-of-the-art vision transformer-based estimator, HELENA reduces inference time by 45.0\% (0.175\,ms vs.\ 0.318\,ms), achieves comparable accuracy (−16.78\,dB vs.\ −17.30\,dB), and requires 8× fewer parameters (0.11M vs.\ 0.88M), demonstrating its suitability for low-latency, real-time deployment.
@article{arxiv.2506.13408,
title = {HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention},
author = {Miguel Camelo Botero and Esra Aycan Beyazit and Nina Slamnik-Kriještorac and Johann M. Marquez-Barja},
journal= {arXiv preprint arXiv:2506.13408},
year = {2026}
}