arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1605.07779cs.LG
收藏

神经通用离散降噪器

Neural Universal Discrete Denoiser

DGIST(大邱庆北科学技术院);Seoul National University(首尔大学)

Taesup Moon, Seonwoo Min, Byunghan Lee, Sungroh Yoon

摘要:

我们提出了一个新的框架,应用深度神经网络(DNN)设计一个通用的离散去噪。与其他利用监督学习进行去噪的方法不同,我们不需要任何额外的训练数据。在这种情况下,虽然地面真理标签,即,干净的数据是不可用的,我们设计了“伪标签”和一个新的目标函数,使得DNN可以以与监督学习相同的方式被训练成离散的去噪器。我们的实验表明,我们得到的算法,被称为神经DUDE,显着优于以前的国家的最先进的几个应用程序与选择超参数,这是一个有吸引力的功能在实践中的系统规则。

英文摘要:

We present a new framework of applying deep neural networks (DNN) to devise a universal discrete denoiser. Unlike other approaches that utilize supervised learning for denoising, we do not require any additional training data. In such setting, while the ground-truth label, i.e., the clean data, is not available, we devise "pseudo-labels" and a novel objective function such that DNN can be trained in a same way as supervised learning to become a discrete denoiser. We experimentally show that our resulting algorithm, dubbed as Neural DUDE, significantly outperforms the previous state-of-the-art in several applications with a systematic rule of choosing the hyperparameter, which is an attractive feature in practice.

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。

↑