论文标题
无监督的神经通用DENOISER用于有限输入通用发出噪声通道
Unsupervised Neural Universal Denoiser for Finite-Input General-Output Noisy Channel
论文作者
论文摘要
我们为有限输入的常规输出（FIGO）通道设计了一种新型的基于神经网络的通用denoiser。基于已知的嘈杂通道密度的假设，在许多实际情况下是现实的，我们训练网络，以便它可以为任何给定的基础干净的源数据而定位，也可以是最佳的滑动窗口denoiser。我们的算法被称为广义Cude（Gen-Cude），具有几种理想的特性。它可以以无监督的方式进行训练（仅基于嘈杂的观察数据），与先前开发的通用deoisiser相比，计算复杂性要小得多，并且在同一环境中具有更严格的上限，这是通过理论分析获得的。在我们的实验中，我们在实践中表明，与其他强大基线相比，合成和实际的基础干净序列相比，Gen-Cude取得了更好的降解结果，从而实现了如此紧密的上限。
We devise a novel neural network-based universal denoiser for the finite-input, general-output (FIGO) channel. Based on the assumption of known noisy channel densities, which is realistic in many practical scenarios, we train the network such that it can denoise as well as the best sliding window denoiser for any given underlying clean source data. Our algorithm, dubbed as Generalized CUDE (Gen-CUDE), enjoys several desirable properties; it can be trained in an unsupervised manner (solely based on the noisy observation data), has much smaller computational complexity compared to the previously developed universal denoiser for the same setting, and has much tighter upper bound on the denoising performance, which is obtained by a theoretical analysis. In our experiments, we show such tighter upper bound is also realized in practice by showing that Gen-CUDE achieves much better denoising results compared to other strong baselines for both synthetic and real underlying clean sequences.
