arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1705.00522cs.LGcs.CV
收藏

正则化残差Quantization:一种多层稀疏字典学习方法

Regularized Residual Quantization: a multi-layer sparse dictionary learning approach

University of Geneva(日内瓦大学)

Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov

摘要:

残差量化(RQ)框架被重新审视,其中量化失真在多层中被连续减少。受率失真理论中的反向注水范例的启发,引入了对码字方差的有效正则化,其允许针对非常大量的层以及针对高维数据扩展RQ,而不会过度训练。所提出的正则化残差量化(RRQ)导致额外稀疏的多层字典,这要归功于当应用于方差衰减数据时正则化的软阈值性质,方差衰减数据可以由应用于相关数据的去相关变换引起。此外,我们还提出了一个通用的预处理自然图像,使他们适合这样的量化。RRQ框架首先在合成方差衰减数据上进行测试,以显示其在高维数据量化方面的效率。接下来,我们在面部图像数据库的超分辨率中使用RRQ,其中示出了来自测试集的低分辨率面部图像,该测试集使用在来自训练集的高分辨率图像上训练的码本量化,当使用这些码本重建时,显示出相关的高频内容。

英文摘要:

The Residual Quantization (RQ) framework is revisited where the quantization distortion is being successively reduced in multi-layers. Inspired by the reverse-water-filling paradigm in rate-distortion theory, an efficient regularization on the variances of the codewords is introduced which allows to extend the RQ for very large numbers of layers and also for high dimensional data, without getting over-trained. The proposed Regularized Residual Quantization (RRQ) results in multi-layer dictionaries which are additionally sparse, thanks to the soft-thresholding nature of the regularization when applied to variance-decaying data which can arise from de-correlating transformations applied to correlated data. Furthermore, we also propose a general-purpose pre-processing for natural images which makes them suitable for such quantization. The RRQ framework is first tested on synthetic variance-decaying data to show its efficiency in quantization of high-dimensional data. Next, we use the RRQ in super-resolution of a database of facial images where it is shown that low-resolution facial images from the test set quantized with codebooks trained on high-resolution images from the training set show relevant high-frequency content when reconstructed with those codebooks.

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。

↑