Machine learning and radiology

S Wang, RM Summers - Medical image analysis, 2012 - Elsevier
In this paper, we give a short introduction to machine learning and survey its applications in
radiology. We focused on six categories of applications in radiology: medical image …

A survey on deep learning-based architectures for semantic segmentation on 2d images

I Ulku, E Akagündüz - Applied Artificial Intelligence, 2022 - Taylor & Francis
Semantic segmentation is the pixel-wise labeling of an image. Boosted by the extraordinary
ability of convolutional neural networks (CNN) in creating semantic, high-level and …

Segnet: A deep convolutional encoder-decoder architecture for image segmentation

V Badrinarayanan, A Kendall… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
We present a novel and practical deep fully convolutional neural network architecture for
semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine …

Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding

A Kendall, V Badrinarayanan, R Cipolla - arxiv preprint arxiv:1511.02680, 2015 - arxiv.org
We present a deep learning framework for probabilistic pixel-wise semantic segmentation,
which we term Bayesian SegNet. Semantic segmentation is an important tool for visual …

Simultaneous detection and segmentation

B Hariharan, P Arbeláez, R Girshick, J Malik - Computer Vision–ECCV …, 2014 - Springer
We aim to detect all instances of a category in an image and, for each instance, mark the
pixels that belong to it. We call this task Simultaneous Detection and Segmentation (SDS) …

Revisiting point cloud shape classification with a simple and effective baseline

A Goyal, H Law, B Liu, A Newell… - … on Machine Learning, 2021 - proceedings.mlr.press
Processing point cloud data is an important component of many real-world systems. As
such, a wide variety of point-based approaches have been proposed, reporting steady …

Deep filter banks for texture recognition and segmentation

M Cimpoi, S Maji, A Vedaldi - Proceedings of the IEEE …, 2015 - openaccess.thecvf.com
Research in texture recognition often concentrates on the problem of material recognition in
uncluttered conditions, an assumption rarely met by applications. In this work we conduct a …

Segnet: A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling

V Badrinarayanan, A Handa, R Cipolla - arxiv preprint arxiv:1505.07293, 2015 - arxiv.org
We propose a novel deep architecture, SegNet, for semantic pixel wise image labelling.
SegNet has several attractive properties;(i) it only requires forward evaluation of a fully learnt …

How to generate cryptographically strong sequences of pseudo random bits

M Blum, S Micali - Providing Sound Foundations for Cryptography: On …, 2019 - dl.acm.org
We introduce a new method of generating sequences of Pseudo Random Bits. Any such
method implies, directly or indirectly, a definition of Randomness. Much effort has been …

[PDF][PDF] What is a good evaluation measure for semantic segmentation?.

G Csurka, D Larlus, F Perronnin, F Meylan - Bmvc, 2013 - projet.liris.cnrs.fr
In this work, we consider the evaluation of the semantic segmentation task. We discuss the
strengths and limitations of the few existing measures, and propose new ways to evaluate …