# Deep Learning Based OFDM Channel Estimation Using Frequency-Time Division and Attention Mechanism

arXiv: https://arxiv.org/abs/2107.07161 · HTML: https://mlsanity.com/paper/2107.07161/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2021.

## Built on by (most cited first, 4 of 4)

- [Channelformer: Attention based Neural Solution for Wireless Channel Estimation and Effective Online Training](https://mlsanity.com/paper/2302.04368/) (2023)
- [Attention Based Neural Networks for Wireless Channel Estimation](https://mlsanity.com/paper/2204.13465/) (2022)
- [Deep OFDM Channel Estimation: Capturing Frequency Recurrence](https://mlsanity.com/paper/2401.05436/) (2024)
- [SwiftChannel: Algorithm-Hardware Co-Design for Deep Learning-Based 5G Channel Estimation](https://mlsanity.com/paper/2605.01931/) (2026)

## Abstract (arXiv)

In this paper, we propose a frequency-time division network (FreqTimeNet) to improve the performance of deep learning (DL) based OFDM channel estimation. This FreqTimeNet is designed based on the orthogonality between the frequency domain and the time domain. In FreqTimeNet, the input is processed by parallel frequency blocks and parallel time blocks sequentially. By introducing the attention mechanism using the SNR information, an attention based FreqTimeNet (AttenFreqTimeNet) is proposed. Using 3rd Generation Partnership Project (3GPP) channel models, the mean square error (MSE) performance of FreqTimeNet and AttenFreqTimeNet under different scenarios is evaluated. A method for constructing mixed training data is proposed, which could address the generalization problem in DL. It is observed that AttenFreqTimeNet outperforms FreqTimeNet, and FreqTimeNet outperforms other DL networks with reasonable complexity.