arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.04731cs.CVcs.AIcs.LG
收藏

反问题的深度学习方法综述

Survey of Deep Learning Methods for Inverse Problems

University of Waterloo(滑铁卢大学)

Shima Kamyab, Zohreh Azimifar, Rasool Sabzi, Paul Fieguth

摘要:

在本文中,我们研究了用于解决逆问题的各种深度学习策略。我们将逆问题的现有深度学习解决方案分为三类:直接映射、数据一致性优化器和深度正则化器。我们选择每种反问题类型的样本,以比较三种类别的鲁棒性,并报告其差异的统计分析。我们进行了广泛的实验上的经典问题的线性回归和三个著名的反问题,在计算机视觉,即图像去噪,3D人脸逆绘制,和对象跟踪,选择作为代表性的原型为每一类的反问题。总体结果和统计分析表明,解决方案类别具有依赖于反问题域的类型的鲁棒性行为,特别是依赖于问题是否包括测量离群值。根据我们的实验结果,我们得出结论,提出最强大的解决方案类别为每个反问题类。

英文摘要:

In this paper we investigate a variety of deep learning strategies for solving inverse problems. We classify existing deep learning solutions for inverse problems into three categories of Direct Mapping, Data Consistency Optimizer, and Deep Regularizer. We choose a sample of each inverse problem type, so as to compare the robustness of the three categories, and report a statistical analysis of their differences. We perform extensive experiments on the classic problem of linear regression and three well-known inverse problems in computer vision, namely image denoising, 3D human face inverse rendering, and object tracking, selected as representative prototypes for each class of inverse problems. The overall results and the statistical analyses show that the solution categories have a robustness behaviour dependent on the type of inverse problem domain, and specifically dependent on whether or not the problem includes measurement outliers. Based on our experimental results, we conclude by proposing the most robust solution category for each inverse problem class.

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。

↑