Learned reconstruction with convergence guarantees

• URL: http://arxiv.org/abs/2206.05431v1
• Date: Sat, 11 Jun 2022 06:08:25 GMT
• Title: Learned reconstruction with convergence guarantees
• Authors: Subhadip Mukherjee, Andreas Hauptmann, Ozan \"Oktem, Marcelo Pereyra, Carola-Bibiane Sch\"onlieb
• Abstract summary: We will specify relevant notions of convergence for data-driven image reconstruction. An example that is highlighted is the role of ICNN, offering the possibility to combine the power of deep learning with classical convex regularization theory.
• Score: 3.9402707512848787
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, deep learning has achieved remarkable empirical success for image reconstruction. This has catalyzed an ongoing quest for precise characterization of correctness and reliability of data-driven methods in critical use-cases, for instance in medical imaging. Notwithstanding the excellent performance and efficacy of deep learning-based methods, concerns have been raised regarding their stability, or lack thereof, with serious practical implications. Significant advances have been made in recent years to unravel the inner workings of data-driven image recovery methods, challenging their widely perceived black-box nature. In this article, we will specify relevant notions of convergence for data-driven image reconstruction, which will form the basis of a survey of learned methods with mathematically rigorous reconstruction guarantees. An example that is highlighted is the role of ICNN, offering the possibility to combine the power of deep learning with classical convex regularization theory for devising methods that are provably convergent. This survey article is aimed at both methodological researchers seeking to advance the frontiers of our understanding of data-driven image reconstruction methods as well as practitioners, by providing an accessible description of convergence concepts and by placing some of the existing empirical practices on a solid mathematical foundation.

Related papers

• Deep End-to-End Survival Analysis with Temporal Consistency [49.77103348208835]
  We present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. A central idea in our method is temporal consistency, a hypothesis that past and future outcomes in the data evolve smoothly over time. Our framework uniquely incorporates temporal consistency into large datasets by providing a stable training signal.
  arXiv  Detail & Related papers  (2024-10-09T11:37:09Z)
• Learned reconstruction methods for inverse problems: sample error estimates [0.8702432681310401]
  This dissertation addresses the generalization properties of learned reconstruction methods, and specifically to perform their sample error analysis. A rather general strategy is proposed, whose assumptions are met for a large class of inverse problems and learned methods.
  arXiv  Detail & Related papers  (2023-12-21T17:56:19Z)
• Enhancing Post-Hoc Explanation Benchmark Reliability for Image Classification [0.0]
  Empirical evaluations demonstrate significant improvements in benchmark reliability across metrics, datasets, and post-hoc methods. This pioneering work establishes a foundation for more reliable evaluation practices in the realm of post-hoc explanation methods.
  arXiv  Detail & Related papers  (2023-11-29T18:21:24Z)
• Two Approaches to Supervised Image Segmentation [55.616364225463066]
  The present work develops comparison experiments between deep learning and multiset neurons approaches. The deep learning approach confirmed its potential for performing image segmentation. The alternative multiset methodology allowed for enhanced accuracy while requiring little computational resources.
  arXiv  Detail & Related papers  (2023-07-19T16:42:52Z)
• Uncertainty Quantification for Deep Unrolling-Based Computational Imaging [0.0]
  We propose a learning-based image reconstruction framework that incorporates the observation model into the reconstruction task. We show that the proposed framework can provide uncertainty information while achieving comparable reconstruction performance to state-of-the-art deep unrolling methods.
  arXiv  Detail & Related papers  (2022-07-02T00:22:49Z)
• Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
  We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms. Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
  arXiv  Detail & Related papers  (2021-11-27T12:12:57Z)
• Deep Reparametrization of Multi-Frame Super-Resolution and Denoising [167.42453826365434]
  We propose a deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks. Our approach is derived by introducing a learned error metric and a latent representation of the target image. We validate our approach through comprehensive experiments on burst denoising and burst super-resolution datasets.
  arXiv  Detail & Related papers  (2021-08-18T17:57:02Z)
• A Survey on Deep Semi-supervised Learning [51.26862262550445]
  We first present a taxonomy for deep semi-supervised learning that categorizes existing methods. We then offer a detailed comparison of these methods in terms of the type of losses, contributions, and architecture differences.
  arXiv  Detail & Related papers  (2021-02-28T16:22:58Z)
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent [4.029853654012035]
  Recent advances in inverse problems leverage powerful data-driven models, e.g., deep neural networks. We develop a scalable, data-driven, knowledge-aided computational framework to quantify the model uncertainty via Bayesian neural networks.
  arXiv  Detail & Related papers  (2020-07-20T09:43:31Z)
• Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation [92.86123832948809]
  We propose a deep face super-resolution (FSR) method with iterative collaboration between two recurrent networks. In each recurrent step, the recovery branch utilizes the prior knowledge of landmarks to yield higher-quality images. A new attentive fusion module is designed to strengthen the guidance of landmark maps.
  arXiv  Detail & Related papers  (2020-03-29T16:04:48Z)
• Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods [0.8263596314702016]
  In this work, we investigate the application of deep learning methods for computed tomography in the context of having a low-data regime. We find that the learned primal-dual has an outstanding performance in terms of reconstruction quality and data efficiency. The proposed methods improve the state-of-the-art results in the low data-regime.
  arXiv  Detail & Related papers  (2020-03-10T21:03:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.