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 2002.11409cs.CV
收藏

深度特征空间中的图像失真解缠

Disentangling Image Distortions in Deep Feature Space

University of Milano - Bicocca(米兰比可卡大学)

Simone Bianco, Luigi Celona, Paolo Napoletano

AI总结:

本文研究深度特征空间中图像失真的内在表征,发现降维特征可分离失真类型,且不同层能力各异,并成功应用于降参考图像质量评估与失真表征。

摘要:

先前文献表明,感知相似性是深度视觉表征所共有的涌现属性。在人类评判图像失真数据集上进行的实验证明,深度特征优于经典感知度量。在本工作中,我们通过分析深度视觉表征内在刻画不同类型图像失真的能力,向更广泛理解该属性迈出进一步步伐。为此,我们首先生成若干合成失真图像,然后分析不同深度神经网络不同层提取的特征。我们观察到,从给定层提取的特征的降维表示能够在特征空间中有效分离失真类型。此外,每个网络层在区分不同类型失真方面表现出不同能力,且该能力随网络架构变化。最后,我们评估利用能更好分离图像失真的层所提取特征,用于:i) 降参考图像质量评估,以及 ii) 在单一和多重失真数据库上对失真类型和严重程度进行表征。两项任务的结果表明,深度视觉表征可无监督地用于高效表征各种图像失真。

英文摘要:

Previous literature suggests that perceptual similarity is an emergent property shared across deep visual representations. Experiments conducted on a dataset of human-judged image distortions have proven that deep features outperform classic perceptual metrics. In this work we take a further step in the direction of a broader understanding of such property by analyzing the capability of deep visual representations to intrinsically characterize different types of image distortions. To this end, we firstly generate a number of synthetically distorted images and then we analyze the features extracted by different layers of different Deep Neural Networks. We observe that a dimension-reduced representation of the features extracted from a given layer permits to efficiently separate types of distortions in the feature space. Moreover, each network layer exhibits a different ability to separate between different types of distortions, and this ability varies according to the network architecture. Finally, we evaluate the exploitation of features taken from the layer that better separates image distortions for: i) reduced-reference image quality assessment, and ii) distortion types and severity levels characterization on both single and multiple distortion databases. Results achieved on both tasks suggest that deep visual representations can be unsupervisedly employed to efficiently characterize various image distortions.

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。

↑