Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency

TL;DR

This paper presents a trustworthy image semantic communication framework that uses GenAI for explainability, controllability, and efficiency, enabling dynamic adaptation and improved interpretability in visual content transmission.

Contribution

The paper introduces a novel ISC framework combining explainable semantics extraction with GenAI and a multi-rate transmission protocol for adaptable, interpretable image communication.

Findings

Achieves explainable learning and decoupled training.

Enables compatible transmission across scenarios.

Demonstrates improved efficiency and interpretability.

Abstract

Image semantic communication (ISC) has garnered significant attention for its potential to achieve high efficiency in visual content transmission. However, existing ISC systems based on joint source-channel coding face challenges in interpretability, operability, and compatibility. To address these limitations, we propose a novel trustworthy ISC framework. This approach leverages text extraction and segmentation mapping techniques to convert images into explainable semantics, while employing Generative Artificial Intelligence (GenAI) for multiple downstream inference tasks. We also introduce a multi-rate ISC transmission protocol that dynamically adapts to both the received explainable semantic content and specific task requirements at the receiver. Simulation results demonstrate that our framework achieves explainable learning, decoupled training, and compatible transmission in various application scenarios. Finally, some intriguing research directions and application scenarios are identified.