no code implementations • 8 Apr 2024 • Hong Ye Tan, Ziruo Cai, Marcelo Pereyra, Subhadip Mukherjee, Junqi Tang, Carola-Bibiane Schönlieb
Unsupervised learning is a training approach in the situation where ground truth data is unavailable, such as inverse imaging problems.
no code implementations • 1 Feb 2024 • Zakhar Shumaylov, Jeremy Budd, Subhadip Mukherjee, Carola-Bibiane Schönlieb
Variational regularisation is the primary method for solving inverse problems, and recently there has been considerable work leveraging deeply learned regularisation for enhanced performance.
no code implementations • 15 Nov 2023 • Marcello Carioni, Subhadip Mukherjee, Hong Ye Tan, Junqi Tang
Together with a detailed survey, we provide an overview of the key mathematical results that underlie the methods reviewed in the chapter to keep our discussion self-contained.
no code implementations • 9 Oct 2023 • Zakhar Shumaylov, Jeremy Budd, Subhadip Mukherjee, Carola-Bibiane Schönlieb
An emerging new paradigm for solving inverse problems is via the use of deep learning to learn a regularizer from data.
no code implementations • 19 Aug 2023 • Mohammad Sadegh Salehi, Subhadip Mukherjee, Lindon Roberts, Matthias J. Ehrhardt
In this work, we propose an algorithm with backtracking line search that only relies on inexact function evaluations and hypergradients and show convergence to a stationary point.
no code implementations • 18 Jul 2023 • Andreas Hauptmann, Subhadip Mukherjee, Carola-Bibiane Schönlieb, Ferdia Sherry
While a significant amount of research has gone into establishing the convergence of the PnP iteration for different regularity conditions on the denoisers, not much is known about the asymptotic properties of the converged solution as the noise level in the measurement tends to zero, i. e., whether PnP methods are provably convergent regularization schemes under reasonable assumptions on the denoiser.
1 code implementation • 17 Apr 2023 • Ziruo Cai, Junqi Tang, Subhadip Mukherjee, Jinglai Li, Carola Bibiane Schönlieb, Xiaoqun Zhang
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.
no code implementations • 20 Mar 2023 • Vasiliki Stergiopoulou, Subhadip Mukherjee, Luca Calatroni, Laure Blanc-Féraud
The spatial resolution of images of living samples obtained by fluorescence microscopes is physically limited due to the diffraction of visible light, which makes the study of entities of size less than the diffraction barrier (around 200 nm in the x-y plane) very challenging.
1 code implementation • 9 Mar 2023 • Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, Carola-Bibiane Schönlieb
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.
no code implementations • 24 Feb 2023 • Simone Saitta, Marcello Carioni, Subhadip Mukherjee, Carola-Bibiane Schönlieb, Alberto Redaelli
4D flow MRI is a non-invasive imaging method that can measure blood flow velocities over time.
no code implementations • 31 Aug 2022 • Junqi Tang, Subhadip Mukherjee, Carola-Bibiane Schönlieb
In this work we propose a new paradigm for designing efficient deep unrolling networks using dimensionality reduction schemes, including minibatch gradient approximation and operator sketching.
no code implementations • 18 Aug 2022 • Debmita Bandyopadhyay, Subhadip Mukherjee, James Ball, Grégoire Vincent, David A. Coomes, Carola-Bibiane Schönlieb
We propose a novel graph-regularized neural network (GRNN) algorithm for tree species classification.
no code implementations • 11 Jun 2022 • Subhadip Mukherjee, Andreas Hauptmann, Ozan Öktem, Marcelo Pereyra, Carola-Bibiane Schönlieb
In recent years, deep learning has achieved remarkable empirical success for image reconstruction.
no code implementations • 21 Mar 2022 • Junqi Tang, Subhadip Mukherjee, Carola-Bibiane Schönlieb
In this work we propose a new paradigm for designing efficient deep unrolling networks using operator sketching.
no code implementations • NeurIPS Workshop Deep_Invers 2021 • Subhadip Mukherjee, Carola-Bibiane Schönlieb, Martin Burger
Variational regularization has remained one of the most successful approaches for reconstruction in imaging inverse problems for several decades.
no code implementations • 19 Oct 2021 • Junqi Tang, Subhadip Mukherjee, Carola-Bibiane Schönlieb
We develop a stochastic (ordered-subsets) variant of the classical learned primal-dual (LPD), which is a state-of-the-art unrolling network for tomographic image reconstruction.
no code implementations • 7 Oct 2021 • Arthur Conmy, Subhadip Mukherjee, Carola-Bibiane Schönlieb
Our proposed approach, which we refer to as learned Bayesian reconstruction with generative models (L-BRGM), entails joint optimization over the style-code and the input latent code, and enhances the expressive power of a pre-trained StyleGAN2 generator by allowing the style-codes to be different for different generator layers.
1 code implementation • NeurIPS 2021 • Subhadip Mukherjee, Marcello Carioni, Ozan Öktem, Carola-Bibiane Schönlieb
We propose an unsupervised approach for learning end-to-end reconstruction operators for ill-posed inverse problems.
1 code implementation • 30 Mar 2021 • Subhadip Mukherjee, Ozan Öktem, Carola-Bibiane Schönlieb
In numerous practical applications, especially in medical image reconstruction, it is often infeasible to obtain a large ensemble of ground-truth/measurement pairs for supervised learning.
1 code implementation • 6 Aug 2020 • Subhadip Mukherjee, Sören Dittmer, Zakhar Shumaylov, Sebastian Lunz, Ozan Öktem, Carola-Bibiane Schönlieb
We consider the variational reconstruction framework for inverse problems and propose to learn a data-adaptive input-convex neural network (ICNN) as the regularization functional.
no code implementations • 2 Oct 2018 • Subhadip Mukherjee, Chandra Sekhar Seelamantula
A comparison with the state-of-the- art algorithms shows that the proposed algorithm has a higher reconstruction accuracy and is about 2 to 3 dB away from the CRB.
no code implementations • 29 Jun 2017 • Subhadip Mukherjee, Deepak R., Huaijin Chen, Ashok Veeraraghavan, Chandra Sekhar Seelamantula
The proposed online algorithm is useful in a setting where one seeks to design a progressive decoding strategy to reconstruct a sparse signal from linear measurements so that one does not have to wait until all measurements are acquired.
no code implementations • 20 May 2017 • Debabrata Mahapatra, Subhadip Mukherjee, Chandra Sekhar Seelamantula
We address the problem of reconstructing sparse signals from noisy and compressive measurements using a feed-forward deep neural network (DNN) with an architecture motivated by the iterative shrinkage-thresholding algorithm (ISTA).
no code implementations • 26 Aug 2014 • Subhadip Mukherjee, Rupam Basu, Chandra Sekhar Seelamantula
We develop a dictionary learning algorithm by minimizing the $\ell_1$ distortion metric on the data term, which is known to be robust for non-Gaussian noise contamination.
no code implementations • 19 Mar 2014 • Subhadip Mukherjee, Chandra Sekhar Seelamantula
We show that the proposed algorithm is efficient in its usage of memory and computational complexity, and performs on par with the standard learning strategy operating on the entire data at a time.