Adaptive CSI Feedback for Deep Learning-Enabled Image Transmission

TL;DR

This paper introduces an adaptive CSI feedback scheme for deep learning-based MIMO image transmission that predicts image quality to optimize feedback overhead, enhancing performance and efficiency.

Contribution

It proposes a novel adaptive CSI feedback method for MIMO JSCC systems that adjusts feedback based on predicted image reconstruction quality, reducing overhead.

Findings

Significant performance improvement with reduced feedback overhead.

Effective prediction of image reconstruction quality.

Enhanced robustness of transmitted images.

Abstract

Recently, deep learning-enabled joint-source channel coding (JSCC) has received increasing attention due to its great success in image transmission. However, most existing JSCC studies only focus on single-input single-output (SISO) channels. In this paper, we first propose a JSCC system for wireless image transmission over multiple-input multiple-output (MIMO) channels. As the complexity of an image determines its reconstruction difficulty, the JSCC achieves quite different reconstruction performances on different images. Moreover, we observe that the images with higher reconstruction qualities are generally more robust to the noise, and can be allocated with less communication resources than the images with lower reconstruction qualities. Based on this observation, we propose an adaptive channel state information (CSI) feedback scheme for precoding, which improves the effectiveness by adjusting the feedback overhead. In particular, we develop a performance evaluator to predict the reconstruction quality of each image, so that the proposed scheme can adaptively decrease the CSI feedback overhead for the transmitted images with high predicted reconstruction qualities in the JSCC system. We perform experiments to demonstrate that the proposed scheme can significantly improve the image transmission performance with much-reduced feedback overhead.