Improving Learning-Based Semantic Coding Efficiency for Image Transmission via Shared Semantic-Aware Codebook

Semantic communications have emerged as a new communication paradigm that extracts and transmits meaningful information relevant to receiver tasks. The trendy semantic coding framework, namely, learning-based joint source-channel coding (JSCC), lies on data-driven principles, with its efficacy depending on the employed neural networks (NNs). This paper introduces a codebook-assisted semantic coding method to improve JSCC performance for image transmission. Notably, a well-constructed codebook is employed to map each source image into a codeword, which subsequently provides shared prior information to assist semantic coding with general NN architectures. The main novelty is two-fold. First, we propose a general semantic-aware codebook construction method based on weighted data-semantic distance. In the case where the semantic information is characterized by discrete labels, this method is refined by encapsulating the labels into codeword indexes. Second, we derive a novel information-theoretic loss function via variational approximation for end-to-end training of the semantic encoder and decoder. This loss function includes a penalty term to mitigate redundancy in the received signals concerning codewords. Extensive experiments conducted over both additive noisy channels and fading channels validate the superior performance of the proposed method with even small-sized codebooks in both image reconstruction and classification accuracy.