Imaging With Equivariant Deep Learning: From unrolled network design to fully unsupervised learning
Imaging With Equivariant Deep Learning: From unrolled network design to fully unsupervised learning
复制标题
DOI：
10.1109/msp.2022.3205430
复制
发表时间：
2022-09
影响因子：
14.9
通讯作者：
Dongdong Chen;M. Davies;Matthias Joachim Ehrhardt;C. Schönlieb;Ferdia Sherry;Julián Tachella
中科院分区：
文献类型：
--
作者：
Dongdong Chen;M. Davies;Matthias Joachim Ehrhardt;C. Schönlieb;Ferdia Sherry;Julián Tachella
从早期的图像处理到现代的计算成像，成功的模型和算法都依赖于自然信号的基本属性：对称性。这里的对称性是指信号集对变换（如平移、旋转或缩放）的不变性。对称性也可以以等方差的形式纳入深度神经网络（DNN），从而实现更有效的数据学习。虽然近年来在设计用于图像分类的端到端等变网络方面取得了重要进展，但计算成像为等变网络解决方案带来了独特的挑战，因为我们通常只能通过一些本身可能不是等变的噪声病态前向算子来观察图像。我们回顾了新兴领域的等变成像（EI），并展示了它如何可以提供改进的泛化和新的成像机会。沿着的方式，我们展示了采集物理和群体行动之间的相互作用，并链接到迭代重建，盲压缩传感和自监督学习。
From early image processing to modern computational imaging, successful models and algorithms have relied on a fundamental property of natural signals: symmetry. Here symmetry refers to the invariance property of signal sets to transformations, such as translation, rotation, or scaling. Symmetry can also be incorporated into deep neural networks (DNNs) in the form of equivariance, allowing for more data-efficient learning. While there have been important advances in the design of end-to-end equivariant networks for image classification in recent years, computational imaging introduces unique challenges for equivariant network solutions since we typically only observe the image through some noisy ill-conditioned forward operator that itself may not be equivariant. We review the emerging field of equivariant imaging (EI) and show how it can provide improved generalization and new imaging opportunities. Along the way, we show the interplay between the acquisition physics and group actions and links to iterative reconstruction, blind compressed sensing, and self-supervised learning.