4 papers
HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compression
Haoxuan Xiong, Yuanyuan Xu, Kun Zhu +2
Learned image compression (LIC) has achieved remarkable coding efficiency, where entropy modeling plays a pivotal role in minimizing bitrate through informative priors. Existing me…
Rethinking Security in Semantic Communication: Latent Manipulation as a New Threat
Zhiyuan Xi, Kun Zhu
Deep learning-based semantic communication (SemCom) has emerged as a promising paradigm for next-generation wireless networks, offering superior transmission efficiency by extracti…
Mentor-Telemachus Bond: Transferring Knowledge in Semantic Communication via Contrastive Learning
Zhiyuan Xi, Kun Zhu, Yuanyuan Xu +1
Encoder, decoder and knowledge base are three major components for semantic communication. Recent advances have achieved significant progress in the encoder-decoder design. However…
Se-HiLo: Noise-Resilient Semantic Communication with High-and-Low Frequency Decomposition
Zhiyuan Xi, Kun Zhu, Yuanyuan Xu
Semantic communication has emerged as a transformative paradigm in next-generation communication systems, leveraging advanced artificial intelligence (AI) models to extract and tra…