Core Concepts
聯合源信道編碼提供了一種端到端的方法,通過優化壓縮和信道編碼來實現更高的性能,特別是在有限長度和時變信道等實際場景中。與傳統的分離式設計相比,聯合編碼可以避免性能下降的"悬崖"和"平台"效應。
Abstract
本文概述了聯合源信道編碼的信息論基礎,回顧了歷年來的實用設計,並討論了其有限採用的原因。隨後重點介紹了基於深度學習的最新進展,即DeepJSCC,並強調其在各種場景下的許多優勢。最後,作者認為現有的嚴格分離架構可能需要重新考慮,以引入聯合編碼來實現高保真、低延遲的關鍵應用通信,如自動駕駛、無人機監視或可穿戴設備。
- 信息論基礎
- 介紹香農的分離定理,說明在某些情況下,聯合編碼可以超越分離設計的性能。
- 討論反饋信道、相關側信息等場景中的聯合編碼方案。
- 分析多用戶信道中分離定理的失效,提出各種聯合編碼方案。
- 介紹不滿足香農假設的新型失真度量的聯合編碼。
- 實用設計
- 回顧傳統的聯合編碼設計方法。
- 重點介紹基於深度學習的DeepJSCC方案,包括圖像、視頻、文本等不同源信號的設計。
- 展望
- 指出現有嚴格分離架構的局限性,呼籲重新考慮引入聯合編碼,以滿足未來關鍵應用的需求。
Stats
以下是支持作者論點的重要數據和統計信息:
"JSCC is known to achieve higher performance in finite blocklength scenarios, and to avoid cliff and the levelling-off effects in time-varying channel scenarios."
"Recent JSCC designs based on neural network architectures report promising results in terms of the end-to-end coding latency."
Quotes
"JSCC offers an alternative end-to-end approach by optimizing compression and channel coding together, or even directly mapping the source signal to the modulated waveform."
"While semantic- and task-oriented compression can be implemented in conventional communication systems, JSCC is known to achieve higher performance in finite blocklength scenarios, and to avoid cliff and the levelling-off effects in time-varying channel scenarios."
"Thanks to the advances in deep learning techniques, particularly through DeepJSCC, JSCC has seen a recent resurgence, highlighting its many surprising advantages in various scenarios."