Fast Equivariant Imaging: Acceleration for Unsupervised Learning via Augmented Lagrangian and Auxiliary PnP Denoisers
This work addresses training efficiency for unsupervised learning in imaging applications, offering a significant speed-up but is incremental as it builds on existing Equivariant Imaging methods.
The authors tackled the problem of slow training in unsupervised deep imaging networks by proposing Fast Equivariant Imaging (FEI), which achieved a 10x acceleration over standard methods while improving generalization in tasks like X-ray CT reconstruction and image inpainting.
In this work, we propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to rapidly and efficiently train deep imaging networks without ground-truth data. From the perspective of reformulating the Equivariant Imaging based optimization problem via the method of Lagrange multipliers and utilizing plug-and-play denoisers, this novel unsupervised scheme shows superior efficiency and performance compared to the vanilla Equivariant Imaging paradigm. In particular, our FEI schemes achieve an order-of-magnitude (10x) acceleration over standard EI on training U-Net for X-ray CT reconstruction and image inpainting, with improved generalization performance.