用随机投影加速图像逆问题中的无监督训练，提升测试时适应效率。
Equivariant Test-Time Training with Operator Sketching for Imaging Inverse Problems
- 引入随机投影压缩等变正则化，降低高维计算开销。
- 在CT和多线圈MRI重建中实现显著提速，测试时训练更高效。
- 仅优化归一化层即可加速训练，适合资源受限场景使用。
等变成像（EI）正则化已成为无监督训练深度成像网络的主流方法，无需真实标签数据。然而，现有基于EI的无监督训练范式在高维应用中存在显著计算冗余，导致效率低下。为此，本文提出一种基于随机投影的压缩版等变正则化（Sketched-EI），利用随机化投影技术实现加速。我们将该方法应用于构建一个加速的深度内部学习框架，可高效用于测试时网络自适应。此外，针对网络适配任务，我们提出一种参数高效策略，仅优化归一化层即可加速标准EI与压缩版EI。在X射线CT和多线圈磁共振成像重建任务上的数值实验表明，该方法相比标准EI可实现显著的计算加速，尤其在测试时训练场景下优势明显。
原文摘要 · Abstract (English)
Equivariant Imaging (EI) regularization has become the de-facto technique for unsupervised training of deep imaging networks, without any need of ground-truth data. Observing that the EI-based unsupervised training paradigm currently has significant computational redundancy leading to inefficiency in high-dimensional applications, we propose a sketched EI regularization which leverages the randomized sketching techniques for acceleration. We apply our sketched EI regularization to develop an accelerated deep internal learning framework, which can be efficiently applied for test-time network adaptation. Additionally, for network adaptation tasks, we propose a parameter-efficient approach to accelerate both EI and Sketched-EI via optimizing only the normalization layers. Our numerical study on X-ray CT and multicoil magnetic resonance image reconstruction tasks demonstrate that our approach can achieve significant computational acceleration over the standard EI counterpart, especially in test-time training tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。