arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.02797cs.ITcs.LGmath.IT
收藏

神经分布式信源编码

Neural Distributed Source Coding

Google DeepMind(谷歌DeepMind);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Jay Whang, Alliot Nagle, Anish Acharya, Hyeji Kim, Alexandros G. Dimakis

AI总结:

本文提出基于条件VQ-VAE的神经分布式信源编码框架,摆脱对特定相关结构的依赖并可扩展至高维,在多个数据集上实现最先进PSNR。

摘要:

分布式信源编码(DSC)是在缺少仅解码器可用的相关边信息的情况下对输入进行编码的任务。值得注意的是,Slepian 和 Wolf 在 1973 年证明,无法访问边信息的编码器可以渐近地达到与拥有边信息时相同的压缩率。尽管该主题已有大量先前工作,但实用的 DSC 一直局限于合成数据集和特定的相关结构。本文提出了一个有损 DSC 框架,该框架对相关结构不敏感,并可扩展到高维数据。我们的方法不依赖手工设计的信源建模,而是利用条件向量量化变分自编码器(VQ-VAE)来学习分布式编码器和解码器。我们在多个数据集上评估了该方法,结果表明其能够处理复杂相关性,并实现了最先进的 PSNR。代码已公开于 https://github.com/acnagle/neural-dsc。

英文摘要:

Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. While there is vast prior work on this topic, practical DSC has been limited to synthetic datasets and specific correlation structures. Here we present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational Autoencoder (VQ-VAE) to learn the distributed encoder and decoder. We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieves state-of-the-art PSNR. Our code is made available at https://github.com/acnagle/neural-dsc.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑