Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TokCom-UEP: Semantic Importance-Matched Unequal Error Protection for Resilient Image Transmission

Kaizheng Zhang, Zuolin Jin, Zhihang Cheng, Ming Zeng, Li Qiao, Zesong Fei

TL;DR

TokCom-UEP targets the nonuniform semantic significance of tokens produced by TokCom by applying semantic importance matched unequal error protection through expanding-window fountain codes. The framework combines head-biased UEP coding with a Multimodal-Guided restoration stage to recover semantically critical tokens under erasure channels, yielding notable improvements in PSNR, perceptual quality LPIPS, and CLIP-based semantic fidelity, especially at low overhead. Experimental results on ImageNet subsets confirm substantial gains over EEP baselines and demonstrate improved spectral efficiency across varying channel erasure conditions, underscoring the value of semantic-aware protection in 6G resilient image transmission.

Abstract

Based on the provided LaTeX code, here is the metadata for the submission form: Title: TokCom-UEP: Semantic Importance-Matched Unequal Error Protection for Resilient Image Transmission Author(s): Kaizheng Zhang, Zuolin Jin, Zhihang Cheng, Ming Zeng, Li Qiao, Zesong Fei Abstract: Token communication (TokCom), an emerging semantic communication framework powered by Large Multimodal Model (LMM), has become a key paradigm for resilient data transmission in 6G networks. A key limitation of existing TokCom designs lies in the assumption of uniform token importance, which leads to the adoption of equal error protection (EEP). However, compressed one-dimensional (1D) token sequences inherently exhibit heterogeneous semantic importance hierarchies, rendering EEP schemes suboptimal. To address this, this paper proposes TokCom-UEP, a novel semantic importance-matched unequal error protection (UEP) framework designed for resilient image transmission. TokCom-UEP integrates rateless UEP coding with the non-uniform semantic importance of tokens by partitioning source tokens into nested expanding windows, assigning higher selection probabilities to windows containing critical tokens to ensure their prioritized recovery. Simulation results demonstrate that TokCom-UEP outperforms EEP schemes in terms of three core semantic restoration metrics and spectral efficiency under low-overhead conditions.

TokCom-UEP: Semantic Importance-Matched Unequal Error Protection for Resilient Image Transmission

TL;DR

TokCom-UEP targets the nonuniform semantic significance of tokens produced by TokCom by applying semantic importance matched unequal error protection through expanding-window fountain codes. The framework combines head-biased UEP coding with a Multimodal-Guided restoration stage to recover semantically critical tokens under erasure channels, yielding notable improvements in PSNR, perceptual quality LPIPS, and CLIP-based semantic fidelity, especially at low overhead. Experimental results on ImageNet subsets confirm substantial gains over EEP baselines and demonstrate improved spectral efficiency across varying channel erasure conditions, underscoring the value of semantic-aware protection in 6G resilient image transmission.

Abstract

Based on the provided LaTeX code, here is the metadata for the submission form: Title: TokCom-UEP: Semantic Importance-Matched Unequal Error Protection for Resilient Image Transmission Author(s): Kaizheng Zhang, Zuolin Jin, Zhihang Cheng, Ming Zeng, Li Qiao, Zesong Fei Abstract: Token communication (TokCom), an emerging semantic communication framework powered by Large Multimodal Model (LMM), has become a key paradigm for resilient data transmission in 6G networks. A key limitation of existing TokCom designs lies in the assumption of uniform token importance, which leads to the adoption of equal error protection (EEP). However, compressed one-dimensional (1D) token sequences inherently exhibit heterogeneous semantic importance hierarchies, rendering EEP schemes suboptimal. To address this, this paper proposes TokCom-UEP, a novel semantic importance-matched unequal error protection (UEP) framework designed for resilient image transmission. TokCom-UEP integrates rateless UEP coding with the non-uniform semantic importance of tokens by partitioning source tokens into nested expanding windows, assigning higher selection probabilities to windows containing critical tokens to ensure their prioritized recovery. Simulation results demonstrate that TokCom-UEP outperforms EEP schemes in terms of three core semantic restoration metrics and spectral efficiency under low-overhead conditions.

Paper Structure

This paper contains 13 sections, 3 equations, 6 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. Tokenization and DeTokenizer
  4. EWF-based UEP coding
  5. Multimodal-Guided Token Restoration
  6. Simulation Results
  7. Experimental Setup
  8. Data and TokCom Model Details
  9. Detailed Communication Setup
  10. Comparative Schemes
  11. Evaluation Metrics
  12. Quantitative Results
  13. Conclusion

Figures (6)

  • Figure 1: The overall architecture of the proposed TokCom-UEP system. The pipeline proceeds sequentially from Image Tokenization to EWF-based UEP Coding, followed by Multimodal-Guided Token Restoration at the receiver, and finally De-tokenization for image reconstruction.
  • Figure 2: Example of EEP and UEP Fountain Code.
  • Figure 3: Comparison of key performance metrics under different MIB selection probability.
  • Figure 4: Comparison of key performance metrics under different overheads.
  • Figure 5: Importance gradually decreases from left to right.
  • ...and 1 more figures