Výsledky vyhledávání - "Vretos, Nicholas"

Report

Comprehensive Comparison of Deep Learning Models for Lung and COVID-19 Lesion Segmentation in CT scans

Autor: Bizopoulos, Paschalis, Vretos, Nicholas, Daras, Petros

Recently there has been an explosion in the use of Deep Learning (DL) methods for medical image segmentation. However the field's reliability is hindered by the lack of a common base of reference for accuracy/performance evaluation and the fact that

Externí odkaz: http://arxiv.org/abs/2009.06412

Zobrazit plný text záznamu

Report

Multi-view adaptive graph convolutions for graph classification

Autor: Adaloglou, Nikolas, Vretos, Nicholas, Daras, Petros

In this paper, a novel multi-view methodology for graph-based neural networks is proposed. A systematic and methodological adaptation of the key concepts of classical deep learning methods such as convolution, pooling and multi-view architectures is

Externí odkaz: http://arxiv.org/abs/2007.12450

Zobrazit plný text záznamu

Report

An Improved Tobit Kalman Filter with Adaptive Censoring Limits

Autor: Loumponias, Kostas, Vretos, Nicholas, Tsaklidis, George, Daras, Petros

This paper deals with the Tobit Kalman filtering (TKF) process when the measurements are correlated and censored. The case of interval censoring, i.e., the case of measurements which belong to some interval with given censoring limits, is considered.

Externí odkaz: http://arxiv.org/abs/1911.06190

Zobrazit plný text záznamu

Report

Non-linear Convolution Filters for CNN-based Learning

Autor: Zoumpourlis, Georgios, Doumanoglou, Alexandros, Vretos, Nicholas, Daras, Petros

During the last years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in image classification. Their architectures have largely drawn inspiration by models of the primate visual system. However, while recent research

Externí odkaz: http://arxiv.org/abs/1708.07038

Zobrazit plný text záznamu