用过拟合实现低复杂度跨模态图像传输，无需训练数据
Leveraging Overfitting for Low-Complexity and Modality-Agnostic Joint Source-Channel Coding
- 为每张图像定制轻量神经解码器，直接优化信道符号
- 每像素仅需641次乘法，参数少至607个，解码复杂度降低1000倍
- 适合流媒体场景，一次离线编码可支持多次在线解码
本文提出Implicit-JSCC，一种新型过拟合联合源信道编码范式，直接优化信道符号和针对每个源的轻量神经解码器。该实例化策略无需训练数据或预训练模型，实现无存储、跨模态的解决方案。作为低复杂度替代方案，Implicit-JSCC在图像传输中实现高效表现，解码复杂度降低约1000倍，每像素仅需641次乘法运算，模型参数仅607个。该过拟合设计天然解决源泛化问题，在高信噪比条件下达到当前最优性能，展现出在流媒体等场景中的巨大潜力，尤其适用于一次离线编码支持多次在线解码的应用。
原文摘要 · Abstract (English)
This paper introduces Implicit-JSCC, a novel overfitted joint source-channel coding paradigm that directly optimizes channel symbols and a lightweight neural decoder for each source. This instance-specific strategy eliminates the need for training datasets or pre-trained models, enabling a storage-free, modality-agnostic solution. As a low-complexity alternative, Implicit-JSCC achieves efficient image transmission with around 1000x lower decoding complexity, using as few as 607 model parameters and 641 multiplications per pixel. This overfitted design inherently addresses source generalizability and achieves state-of-the-art results in the high SNR regimes, underscoring its promise for future communication systems, especially streaming scenarios where one-time offline encoding supports multiple online decoding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。