Online Deep Equilibrium Learning for Regularization by Denoising

• URL: http://arxiv.org/abs/2205.13051v1
• Date: Wed, 25 May 2022 21:06:22 GMT
• Title: Online Deep Equilibrium Learning for Regularization by Denoising
• Authors: Jiaming Liu, Xiaojian Xu, Weijie Gan, Shirin Shoushtari, Ulugbek S. Kamilov
• Abstract summary: Plug-and-Play Equilibrium Priors (memory) and Regularization by Denoising (RED) are widely-used frameworks for solving inverse imaging problems by computing fixed-points. We propose ODER as a new strategy for improving the efficiency of DEQ/RED on the total number of measurements. Our numerical results suggest the potential improvements in training/testing complexity due to ODER on three distinct imaging applications.
• Score: 20.331171081002957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Plug-and-Play Priors (PnP) and Regularization by Denoising (RED) are widely-used frameworks for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image priors. While traditional PnP/RED formulations have focused on priors specified using image denoisers, there is a growing interest in learning PnP/RED priors that are end-to-end optimal. The recent Deep Equilibrium Models (DEQ) framework has enabled memory-efficient end-to-end learning of PnP/RED priors by implicitly differentiating through the fixed-point equations without storing intermediate activation values. However, the dependence of the computational/memory complexity of the measurement models in PnP/RED on the total number of measurements leaves DEQ impractical for many imaging applications. We propose ODER as a new strategy for improving the efficiency of DEQ through stochastic approximations of the measurement models. We theoretically analyze ODER giving insights into its convergence and ability to approximate the traditional DEQ approach. Our numerical results suggest the potential improvements in training/testing complexity due to ODER on three distinct imaging applications.

Related papers

• EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models [70.60381055741391]
  Image restoration challenges related to illposed problems, resulting in deviations between single model predictions and ground-truths. Ensemble learning aims to address these deviations by combining the predictions of multiple base models. We employ an expectation (EM)-based algorithm to estimate ensemble weights for prediction candidates. Our algorithm is model-agnostic and training-free, allowing seamless integration and enhancement of various pre-trained image restoration models.
  arXiv  Detail & Related papers  (2024-10-30T12:16:35Z)
• An Optimization-based Deep Equilibrium Model for Hyperspectral Image Deconvolution with Convergence Guarantees [71.57324258813675]
  We propose a novel methodology for addressing the hyperspectral image deconvolution problem. A new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network. The derived iterative solver is then expressed as a fixed-point calculation problem within the Deep Equilibrium framework.
  arXiv  Detail & Related papers  (2023-06-10T08:25:16Z)
• Poisson-Gaussian Holographic Phase Retrieval with Score-based Image Prior [19.231581775644617]
  We propose a new algorithm called "AWFS" that uses the accelerated Wirtinger flow (AWF) with a score function as generative prior. We calculate the gradient of the log-likelihood function for PR and determine the Lipschitz constant. We provide theoretical analysis that establishes a critical-point convergence guarantee for the proposed algorithm.
  arXiv  Detail & Related papers  (2023-05-12T18:08:47Z)
• On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent [13.168923974530307]
  Methods to solve imaging problems usually combine an explicit data likelihood function with a prior that explicitly expected properties of the solution. In a departure from explicit modelling, several recent works have proposed and studied the use of implicit priors defined by an image denoising algorithm.
  arXiv  Detail & Related papers  (2022-01-16T20:50:08Z)
• Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition [48.08511796234349]
  We show how to establish theoretical recovery guarantees for the plug-and-play priors (noise) and regularization by denoising (RED) methods. Our results suggest that models with a pre-trained artifact removal network provides significantly better results compared to existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-07T14:45:38Z)
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems [22.239477171296056]
  Plug-and-Play (MM) is a non- optimization framework that combines numerical algorithms, for example, with advanced denoising priors. We discuss several practical considerations of more denoisers, which together with our learned strategies are state-of-the-art results.
  arXiv  Detail & Related papers  (2020-11-18T14:19:30Z)
• Shared Prior Learning of Energy-Based Models for Image Reconstruction [69.72364451042922]
  We propose a novel learning-based framework for image reconstruction particularly designed for training without ground truth data. In the absence of ground truth data, we change the loss functional to a patch-based Wasserstein functional. In shared prior learning, both aforementioned optimal control problems are optimized simultaneously with shared learned parameters of the regularizer.
  arXiv  Detail & Related papers  (2020-11-12T17:56:05Z)
• Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints [80.60538408386016]
  Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry. We propose an end-to-end trainable framework consisting of learnable modules for detection, feature extraction, matching and outlier rejection.
  arXiv  Detail & Related papers  (2020-07-29T21:41:31Z)
• A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding [57.1077544780653]
  We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems. We focus on convex games, solved by local agents represented by the nodes of a graph and interacting through regularization functions. This approach is appealing for solving imaging problems, as it allows the use of classical image priors within deep models that are trainable end to end.
  arXiv  Detail & Related papers  (2020-06-26T08:34:54Z)
• Scalable Plug-and-Play ADMM with Convergence Guarantees [24.957046830965822]
  We propose an incremental variant of the widely used. ADMM algorithm, making it scalable to large-scale datasets. We theoretically analyze the convergence algorithm under a set explicit assumptions.
  arXiv  Detail & Related papers  (2020-06-05T04:10:15Z)
• Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems [22.239477171296056]
  Plug-and-play () is a non customize framework that combines different learned algorithms with advanced denoiser priors. A key problem. based approaches is that they require manual parameter tweaking. A key part of our approach is develop a network policy for automatic tuning of parameters. We show promising results on Compressed Sensing and phase retrieval.
  arXiv  Detail & Related papers  (2020-02-22T03:09:48Z)

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.