arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1704.01372cs.CV
收藏

彩色图像去噪与分类的关系

On the Relation between Color Image Denoising and Classification

ETH Zurich(苏黎世联邦理工学院)

Jiqing Wu, Radu Timofte, Zhiwu Huang, Luc Van Gool

摘要:

大量的图像去噪文献主要集中在单通道图像上,并且通常最多在数十幅图像上对所提出的方法进行实验验证。本文研究了大规模数据集上去噪和分类之间的相互作用。受分类模型的启发,我们提出了一种用于彩色(多通道)图像去噪的新型深度学习架构,并报告了来自ImageNet数据集的数千张图像以及常用图像。我们研究了(足够的)训练数据的重要性,如何语义类信息可以被交易,以改善去噪结果。因此,我们的方法大大提高了PSNR性能的0.34 - 0.51 dB的大规模数据集上的最先进的方法平均。我们的结论是,这是有益的,纳入分类模型。另一方面,我们还研究了噪声如何影响分类性能。最后,我们得出了一些有趣的结论,有些是违反直觉的。

英文摘要:

Large amount of image denoising literature focuses on single channel images and often experimentally validates the proposed methods on tens of images at most. In this paper, we investigate the interaction between denoising and classification on large scale dataset. Inspired by classification models, we propose a novel deep learning architecture for color (multichannel) image denoising and report on thousands of images from ImageNet dataset as well as commonly used imagery. We study the importance of (sufficient) training data, how semantic class information can be traded for improved denoising results. As a result, our method greatly improves PSNR performance by 0.34 - 0.51 dB on average over state-of-the art methods on large scale dataset. We conclude that it is beneficial to incorporate in classification models. On the other hand, we also study how noise affect classification performance. In the end, we come to a number of interesting conclusions, some being counter-intuitive.

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。

↑