Zobrazeno 1 - 10
of 170
pro vyhledávání: '"Tang, Junqi"'
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
Externí odkaz:
http://arxiv.org/abs/2411.05771
The manifold hypothesis says that natural high-dimensional data is actually supported on or around a low-dimensional manifold. Recent success of statistical and learning-based methods empirically supports this hypothesis, due to outperforming classic
Externí odkaz:
http://arxiv.org/abs/2408.06996
Stochastic optimisation algorithms are the de facto standard for machine learning with large amounts of data. Handling only a subset of available data in each optimisation step dramatically reduces the per-iteration computational costs, while still e
Externí odkaz:
http://arxiv.org/abs/2406.06342
Autor:
Tan, Hong Ye, Cai, Ziruo, Pereyra, Marcelo, Mukherjee, Subhadip, Tang, Junqi, Schönlieb, Carola-Bibiane
Imaging is a standard example of an inverse problem, where the task of reconstructing a ground truth from a noisy measurement is ill-posed. Recent state-of-the-art approaches for imaging use deep learning, spearheaded by unrolled and end-to-end model
Externí odkaz:
http://arxiv.org/abs/2404.05445
The Condat-V\~u algorithm is a widely used primal-dual method for optimizing composite objectives of three functions. Several algorithms for optimizing composite objectives of two functions are special cases of Condat-V\~u, including proximal gradien
Externí odkaz:
http://arxiv.org/abs/2403.17100
Unsupervised deep learning approaches have recently become one of the crucial research areas in imaging owing to their ability to learn expressive and powerful reconstruction operators even when paired high-quality training data is scarcely available
Externí odkaz:
http://arxiv.org/abs/2311.08972
Learning-to-optimize (L2O) is an emerging research area in large-scale optimization with applications in data science. Recently, researchers have proposed a novel L2O framework called learned mirror descent (LMD), based on the classical mirror descen
Externí odkaz:
http://arxiv.org/abs/2308.05045
Combining the strengths of model-based iterative algorithms and data-driven deep learning solutions, deep unrolling networks (DuNets) have become a popular tool to solve inverse imaging problems. While DuNets have been successfully applied to many li
Externí odkaz:
http://arxiv.org/abs/2307.16120
Autor:
Cai, Ziruo, Tang, Junqi, Mukherjee, Subhadip, Li, Jinglai, Schönlieb, Carola Bibiane, Zhang, Xiaoqun
Bayesian methods for solving inverse problems are a powerful alternative to classical methods since the Bayesian approach offers the ability to quantify the uncertainty in the solution. In recent years, data-driven techniques for solving inverse prob
Externí odkaz:
http://arxiv.org/abs/2304.08342
Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA or ADMM, with applications in inverse problems and imaging. Provab
Externí odkaz:
http://arxiv.org/abs/2303.07271