Block Erasure-Aware Semantic Multimedia Compression via JSCC Autoencoder

2026-01-28

AI Summary

This work addresses semantic information loss and high retransmission latency caused by block erasures in bandwidth-constrained, time-varying channels. The authors propose a block-erasure-aware semantic compression framework built upon a joint source-channel coding (JSCC) autoencoder. Integrating deep learning–driven semantic encoding, block-erasure-aware training, and a transmission mechanism compatible with existing network protocols, the framework enables intelligent congestion control and unequal error protection. Through tunable parameters, it ensures semantic robustness under poor channel conditions while preserving high fidelity when channel quality is good, thereby achieving graceful degradation and high-quality semantic reconstruction across varying channel states. Experiments demonstrate that the proposed method significantly outperforms state-of-the-art approaches in both image and video tasks, offering superior resilience to packet loss and enhanced semantic recovery quality.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We present an AI-based framework for semantic transmission of multimedia data over band-limited, time-varying channels. The method targets scenarios where large content is split into multiple packets, with an unknown number potentially dropped due to channel impairments. Using joint source-channel coding (JSCC), our approach achieves reliable semantic reconstruction with graceful quality degradation as channel conditions worsen, eliminating the need for retransmissions that cause unacceptable delays in latency-sensitive applications such as video conferencing and robotic control. The framework is compatible with existing network protocols and further enables intelligent congestion control and unequal error protection. A tunable design parameter allows balancing robustness at low channel quality against fidelity at high channel quality. Experiments demonstrate significant robustness improvement over state-of-the-art baselines in both image and video domains.

Problem

• semantic communication
• block erasure
• multimedia compression
• joint source-channel coding
• latency-sensitive transmission

Innovation

• semantic communication
• joint source-channel coding (JSCC)
• block erasure resilience
• multimedia compression
• graceful degradation