End-to-end reconstruction meets data-driven regularization for inverse problems
Dec 6, 2021
Speakers
Subhadip Mukherjee
Speaker · 0 followers
Marcello Carioni
Speaker · 0 followers
Ozan Öktem
Speaker · 0 followers
Carola-Bibiane Schönlieb
Speaker · 0 followers
About
We propose an unsupervised approach for learning end-to-end reconstruction operators for ill-posed inverse problems. The proposed method combines the classical variational framework with iterative unrolling, which essentially seeks to minimize a weighted combination of the expected distortion in the measurement space and the Wasserstein-1 distance between the distributions of the reconstruction and ground-truth. More specifically, the regularizer in the variational setting is parametrized by a deep neural network and learned simultaneously with the unrolled reconstruction operator. The variational problem is then initialized with the reconstruction of the unrolled operator and solved iteratively till convergence. Notably, it takes significantly fewer iterations to converge, thanks to the excellent initialization obtained via the unrolled operator. The resulting approach combines the computational efficiency of end-to-end unrolled reconstruction with the well-posedness and noise-stability guarantees of the variational setting. Moreover, we demonstrate with the example of X-ray computed tomography (CT) that our approach outperforms state-of-the-art unsupervised methods, and that it outperforms or is on par with state-of-the-art supervised learned reconstruction approaches.We propose an unsupervised approach for learning end-to-end reconstruction operators for ill-posed inverse problems. The proposed method combines the classical variational framework with iterative unrolling, which essentially seeks to minimize a weighted combination of the expected distortion in the measurement space and the Wasserstein-1 distance between the distributions of the reconstruction and ground-truth. More specifically, the regularizer in the variational setting is parametrized by a d…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression
Watch later
Zhize Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
Watch later
Total of 2 viewers voted for saving the presentation to eternal vault which is 0.2%
Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Call to Action
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Convergence of adaptive algorithms for constrained weakly convex optimization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Supporting human flourishing by ensuring human involvement in AI systems
Watch later
Joel Chan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%