Efficient Semantic Communication Through Transformer-Aided Compression
This work addresses the problem of efficient image transmission in limited bandwidth conditions for wireless communication systems, representing an incremental improvement by adapting existing transformer methods to dynamic channel constraints.
The paper tackles the problem of transmitting images efficiently over time-varying wireless channels by introducing a channel-aware adaptive framework that uses vision transformers to compress image patches at different rates based on semantic content and channel bandwidth. The results show that the approach maintains high semantic fidelity while optimizing bandwidth, as evaluated on the TinyImageNet dataset with measurements of reconstruction quality and accuracy.
Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication systems. In this work, we introduce a channel-aware adaptive framework for semantic communication, where different regions of the image are encoded and compressed based on their semantic content. By employing vision transformers, we interpret the attention mask as a measure of the semantic contents of the patches and dynamically categorize the patches to be compressed at various rates as a function of the instantaneous channel bandwidth. Our method enhances communication efficiency by adapting the encoding resolution to the content's relevance, ensuring that even in highly constrained environments, critical information is preserved. We evaluate the proposed adaptive transmission framework using the TinyImageNet dataset, measuring both reconstruction quality and accuracy. The results demonstrate that our approach maintains high semantic fidelity while optimizing bandwidth, providing an effective solution for transmitting multi-resolution data in limited bandwidth conditions.