论文标题
分析性深层方法的正则化理论
Regularization Theory of the Analytic Deep Prior Approach
论文作者
论文摘要
最近引入了分析深度先验方法（ADP）方法，用于具有特殊网络体系结构的深层图像先验方法（DIP）方法的理论分析。在本文中，我们证明ADP实际上等同于经典的伊万诺夫方法来解决不良反向问题。此外，我们提出了一种新的变体，该变体将早期停止的策略纳入了ADP模型。对于这两种变体，我们都会显示如何在共同假设下获得经典的正则特性（存在，稳定，收敛）。
The analytic deep prior (ADP) approach was recently introduced for the theoretical analysis of deep image prior (DIP) methods with special network architectures. In this paper, we prove that ADP is in fact equivalent to classical variational Ivanov methods for solving ill-posed inverse problems. Besides, we propose a new variant which incorporates the strategy of early stopping into the ADP model. For both variants, we show how classical regularization properties (existence, stability, convergence) can be obtained under common assumptions.
