HELENA: High-Efficiency Learning-Based Channel Estimation Using Dual Neural Attention
Accurate channel estimation is critical for highperformance Orthogonal Frequency-Division Multiplexing (OFDM) systems, particularly at low signal-to-noise ratios and under stringent latency constraints. This paper presents High-Efficiency Learning-based channel Estimation using dual Neural Attention (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% (0.175ms vs. 0.318ms), achieves comparable accuracy ($- 1 6. 7 8 \text{dB}$ vs. $-1 7. 3 0 \text{dB}$), and requires $8 \times$ fewer parameters ($0. 1 1 \mathrm{M}$ vs. $0. 8 8 \mathrm{M}$), demonstrating its suitability for low-latency, real-time OFDM-based wireless systems.