Untrained Graph Neural Networks for Denoising

Rey, Samuel; Segarra, Santiago; Heckel, Reinhard; Marqués, Antonio G.

doi:10.1109/tsp.2022.3223552

Cited by 14 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through deep learning techniques, neural networks can automatically learn features and patterns in images to achieve more accurate noise reduction. Among them, Convolutional Neural Network (CNN) is the most widely used type of neural network, which performs well in image processing tasks [12,13]. The core idea of neural network is to learn and extract image features at various scales through a series of convolutional, pooling and fully connected layers, so as to achieve image noise reduction.…”

Section: Methods Based On Machine Learningmentioning

confidence: 99%

Effect Analysis of Fourier Transform and Neural Network on Image Noise Reduction

Yang

2024

HSET

View full text Add to dashboard Cite

During the acquisition, transmission, and processing of digital images, noise often appears in the pictures, seriously affecting the quality of the images and the accuracy of subsequent analysis. To solve this problem, many scholars have conducted in-depth research on image denoising, aiming to find denoising methods suitable for different scenarios. This study aims to compare the effects of Fourier transform and neural network methods in eliminating stripes in pictures. The discrete Fourier transform denoising method performs best in sharpness and has a fast processing time, but its image restoration is poor. Although the artificial neural network method has a long processing time and depends on the training set, it has good noise reduction effect. The Photoshop (beta) method is relatively simple and easy to use, with good overall effect. It is hoped that through further research, a better understanding of the role of Fourier transform and neural network methods in image noise elimination can be achieved, providing more references for the development of image processing technology. This article introduces in detail the Fourier transform method and neural network method, analyzes their advantages and disadvantages and scope of application. These results shed light on guiding further exploration of noise reduction.

show abstract

Section: Methods Based On Machine Learningmentioning

confidence: 99%

Effect Analysis of Fourier Transform and Neural Network on Image Noise Reduction

Yang

2024

HSET

View full text Add to dashboard Cite

show abstract

“…Nevertheless, not only is DeepL usually training-data hungry and computationally heavy, but concerns were also raised in [23] about instabilities in medical-image reconstruction. Deep image priors (DIP) [24] and untrained neural networks offer user-defined priors to alleviate the need for massive training data, and have been used in signal recovery [25], [26] and accelerated medical imaging [27], [28].…”

Section: Introductionmentioning

confidence: 99%

Multilinear Kernel Regression and Imputation via Manifold Learning

Nguyen,

Slavakis

2024

Preprint

View full text Add to dashboard Cite

This paper introduces a novel nonparametric framework for data imputation, coined multilinear kernel regression and imputation via the manifold assumption (MultiL-KRIM). Motivated by manifold learning, MultiL-KRIM models data features as a point cloud located in or close to a user-unknown smooth manifold embedded in a reproducing kernel Hilbert space. Unlike typical manifold-learning routes, which seek low-dimensional patterns via regularizers based on graph-Laplacian matrices, MultiL-KRIM builds instead on the intuitive concept of tangent spaces to manifolds and incorporates collaboration among point-cloud neighbors (regressors) directly into the data modeling term of the loss function. Multiple kernel functions are allowed to offer robustness and rich approximation properties, while multiple matrix factors offer low-rank modeling, integrate dimensionality reduction, and streamline computations with no need of training data. Two important application domains showcase the functionality of MultiL-KRIM: time-varying graph-signal (TVGS) recovery, and reconstruction of highly accelerated dynamic-magnetic-resonance-imaging (dMRI) data. Extensive numerical tests on real and synthetic data demonstrate MultiL-KRIM’s remarkable speedups over its predecessors, and outperformance over prevalent “shallow” data-imputation techniques, with a more intuitive and explainable pipeline than deep-image-prior methods.

show abstract

“…Complex signal denoising has been demonstrated in automotive applications based on spectrograms being fed as complex-valued images into a CNN [39], but this is simulated additive white Gaussian noise which is not correlated. In [40], untrained graph neural networks directly estimate the raw signal parameters faster than noise alike one-shot learning showing promise as it has been validated over simulated and real data. This area, however, for complex signals is still undergoing development.…”

Section: Introductionmentioning

confidence: 99%

Radar‐based human activity recognition using denoising techniques to enhance classification accuracy

Yu,

Du,

et al. 2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Radar‐based human activity recognition is considered as a competitive solution for the elderly care health monitoring problem, compared to alternative techniques such as cameras and wearable devices. However, raw radar signals are often contaminated with noise, clutter, and other artifacts that significantly impact recognition performance, which highlights the importance of prepossessing techniques that enhance radar data quality and improve classification model accuracy. In this study, two different human activity classification models incorporated with pre‐processing techniques have been proposed. The authors introduce wavelet denoising methods into a cyclostationarity‐based classification model, resulting in a substantial improvement in classification accuracy. To address the limitations of conventional pre‐processing techniques, a deep neural network model called Double Phase Cascaded Denoising and Classification Network (DPDCNet) is proposed, which performs end‐to‐end signal‐level classification and achieves state‐of‐the‐art accuracy. The proposed models significantly reduce false detections and would enable robust activity monitoring for older individuals with radar signals, thereby bringing the system closer to a practical implementation for deployment.

show abstract

Untrained Graph Neural Networks for Denoising

Cited by 14 publications

References 43 publications

Effect Analysis of Fourier Transform and Neural Network on Image Noise Reduction

Effect Analysis of Fourier Transform and Neural Network on Image Noise Reduction

Multilinear Kernel Regression and Imputation via Manifold Learning

Radar‐based human activity recognition using denoising techniques to enhance classification accuracy

Contact Info

Product

Resources

About