Phase retrieval (PR) is an important component in modern computational imaging systems. Many algorithms have been developed over the past half century. Recent advances in deep learning have opened up a new possibility for robust and fast PR. An emerging technique, called deep unfolding, provides a systematic connection between conventional model-based iterative algorithms and modern data-based deep learning. Unfolded algorithms, powered by data learning, have shown remarkable performance and convergence speed improvement over the original algorithms. Despite their potential, most existing unfolded algorithms are strictly confined to a fixed number of iterations when employing layer-dependent parameters. In this study, we develop a novel framework for deep unfolding to overcome the existing limitations. Even if our framework can be widely applied to general inverse problems, we take PR as an example in the paper. Our development is based on an unfolded generalized expectation consistent signal recovery (GEC-SR) algorithm, wherein damping factors are left for data-driven learning. In particular, we introduce a hypernetwork to generate the damping factors for GEC-SR. Instead of directly learning a set of optimal damping factors, the hypernetwork learns how to generate the optimal damping factors according to the clinical settings, thus ensuring its adaptivity to different scenarios. To make the hypernetwork work adapt to varying layer numbers, we use a recurrent architecture to develop a dynamic hypernetwork, which generates a damping factor that can vary online across layers. We also exploit a self-attention mechanism to enhance the robustness of the hypernetwork. Extensive experiments show that the proposed algorithm outperforms existing ones in convergence speed and accuracy, and still works well under very harsh settings, that many classical PR algorithms unstable or even fail.
翻译:阶段检索(PR)是现代计算成像系统的一个重要组成部分。 许多演算法在过去半个世纪里已经发展了。 最近的深层次学习进步为稳健和快速的PR开辟了一个新的可能性。 一种新兴技术,称为深层演化,提供了传统基于模型的迭代算法与现代基于数据的深层学习之间的系统联系。 由数据学习驱动的未翻版算法显示了与原始算法相比的显著性能和趋同速度的改进。 尽管它们具有潜力,但大多数现有的演算法在使用基于层的参数时严格限于固定的迭代数。 在本研究中,我们为深度演进提供了一个新的框架,以克服现有的限制。 即使我们的框架可以被广泛应用于一般的反向问题,我们也以PR为例。 我们的发展是基于一种普遍期待的一致信号恢复(GEC-SR)算法,其中的偏差因素留给了数据驱动的学习。 特别是,我们引入了一个超额网络,以生成一个精确的缩略因素。 而不是直接学习一套最佳的测算因素, 超额网络学会学会学习如何在现有的精确的精确地构造中学习如何调整, 。 如何使不断的不断的不断变现的机变现的机能结构在不断变动的自我结构中, 我们的自我变动的变动的机能的变动的变动的变动的变动的变压, 将它能的机能到到的机, 使它能的机能到的机能到一个最深的造的造的机能的机能的机能到一个比。