4.6 Article

Joint Reconstruction-Segmentation on Graphs

Related references

Note: Only part of the references are listed.
Article Mathematics, Applied

Task adapted reconstruction for inverse problems

Jonas Adler et al.

Summary: This paper discusses how to perform a post-processing task on a model parameter in an ill-posed inverse problem, where the parameter is only indirectly observed through noisy data. The authors propose a framework based on (deep) neural networks to formalize the reconstruction and post-processing steps as statistical estimation problems. By jointly training the networks against suitable supervised training data, an end-to-end task adapted reconstruction method is obtained. The suggested framework is generic and adaptable, allowing for customization of the inverse problem and post-processing task. The approach is demonstrated on joint tomographic image reconstruction, classification, and segmentation.

INVERSE PROBLEMS (2022)

Proceedings Paper Computer Science, Interdisciplinary Applications

Graph-based Active Learning for Semi-supervised Classification of SAR Data

Kevin Miller et al.

Summary: The article presents a novel method for classifying Synthetic Aperture Radar (SAR) data using a combination of graph-based learning and neural network methods. The method uses a Convolutional Neural Network Variational Autoencoder (CNNVAE) to embed SAR data into a feature space, and then constructs a similarity graph for classification. The method reduces overfitting and improves generalization performance, and can be easily combined with human-in-the-loop active learning.

ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXIX (2022)

Article Mathematics, Applied

PDES ON GRAPHS FOR SEMI-SUPERVISED LEARNING APPLIED TO FIRST-PERSON ACTIVITY RECOGNITION IN BODY-WORN VIDEO

Hao Li et al.

Summary: This paper demonstrates the use of PDE-based graph methods for modern machine learning applications, focusing on a case study of body-worn video classification. By utilizing physics-based machine learning with classical ideas like optical flow, along with linear mixture models and PDE-based graph classification methods, it allows for effective video analysis with modest training data while also protecting privacy.

DISCRETE AND CONTINUOUS DYNAMICAL SYSTEMS (2021)

Article Computer Science, Artificial Intelligence

Collaborative Filtering of Correlated Noise: Exact Transform-Domain Variance for Improved Shrinkage and Patch Matching

Ymir Makinen et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

Article Mathematics, Applied

GRAPH MERRIMAN-BENCE-OSHER AS A SEMIDISCRETE IMPLICIT EULER SCHEME FOR GRAPH ALLEN-CAHN FLOW

Jeremy Budd et al.

SIAM JOURNAL ON MATHEMATICAL ANALYSIS (2020)

Article Mathematics, Applied

Enhancing joint reconstruction and segmentation with non-convex Bregman iteration

Veronica Corona et al.

INVERSE PROBLEMS (2019)

Article Mathematics

Solving inverse problems using data-driven models

Simon Arridge et al.

ACTA NUMERICA (2019)

Article Computer Science, Theory & Methods

Calculus of the Exponent of Kurdyka-Aojasiewicz Inequality and Its Applications to Linear Convergence of First-Order Methods

Guoyin Li et al.

FOUNDATIONS OF COMPUTATIONAL MATHEMATICS (2018)

Article Computer Science, Artificial Intelligence

Graph Clustering, Variational Image Segmentation Methods and Hough Transform Scale Detection for Object Measurement in Images

Luca Calatroni et al.

JOURNAL OF MATHEMATICAL IMAGING AND VISION (2017)

Article Computer Science, Artificial Intelligence

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Kai Zhang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2017)

Article Computer Science, Artificial Intelligence

Convex Variational Methods on Graphs for Multiclass Segmentation of High-Dimensional Data and Point Clouds

Egil Bae et al.

JOURNAL OF MATHEMATICAL IMAGING AND VISION (2017)

Article Physics, Mathematical

Convergence of the Graph Allen-Cahn Scheme

Xiyang Luo et al.

JOURNAL OF STATISTICAL PHYSICS (2017)

Article Computer Science, Artificial Intelligence

Multiclass Data Segmentation Using Diffuse Interface Methods on Graphs

Cristina Garcia-Cardona et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2014)

Article Mathematics, Applied

Mean Curvature, Threshold Dynamics, and Phase Field Theory on Finite Graphs

Yves van Gennip et al.

MILAN JOURNAL OF MATHEMATICS (2014)

Article Computer Science, Software Engineering

Proximal alternating linearized minimization for nonconvex and nonsmooth problems

Jerome Bolte et al.

MATHEMATICAL PROGRAMMING (2014)

Article Operations Research & Management Science

A Primal-Dual Splitting Method for Convex Optimization Involving Lipschitzian, Proximable and Linear Composite Terms

Laurent Condat

JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS (2013)

Article Computer Science, Artificial Intelligence

An MBO Scheme on Graphs for Classification and Image Processing

Ekaterina Merkurjev et al.

SIAM JOURNAL ON IMAGING SCIENCES (2013)

Article Computer Science, Software Engineering

RudinOsherFatemi Total Variation Denoising using Split Bregman

Pascal Getreuer

IMAGE PROCESSING ON LINE (2012)

Article Computer Science, Software Engineering

Total Variation Deconvolution using Split Bregman

Pascal Getreuer

IMAGE PROCESSING ON LINE (2012)

Article Computer Science, Artificial Intelligence

A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging

Antonin Chambolle et al.

JOURNAL OF MATHEMATICAL IMAGING AND VISION (2011)

Article Operations Research & Management Science

Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Lojasiewicz Inequality

Hedy Attouch et al.

MATHEMATICS OF OPERATIONS RESEARCH (2010)

Article Computer Science, Artificial Intelligence

Active contours driven by local image fitting energy

Kaihua Zhang et al.

PATTERN RECOGNITION (2010)

Article Computer Science, Artificial Intelligence

Total Generalized Variation

Kristian Bredies et al.

SIAM JOURNAL ON IMAGING SCIENCES (2010)

Article Computer Science, Interdisciplinary Applications

A Mumford-Shah level-set approach for the inversion and segmentation of X-ray tomography data

Ronny Ramlau et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2007)

Article Computer Science, Interdisciplinary Applications

Threshold dynamics for the piecewise constant Mumford-Shah functional

S Esedoglu et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2006)

Article Computer Science, Artificial Intelligence

Image segmentation and selective smoothing by using Mumford-Shah model

S Gao et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2005)

Article Computer Science, Artificial Intelligence

A statistical approach to texture classification from single images

M Varma et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2005)

Article Computer Science, Artificial Intelligence

Spectral grouping using the Nystrom method

C Fowlkes et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2004)

Article Computer Science, Artificial Intelligence

Active contours without edges

TF Chan et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2001)