Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Niamh Belton"'
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::217c7b03b45072780d7f1049eb678bc7
https://doi.org/10.1109/icassp49357.2023.10096505
https://doi.org/10.1109/icassp49357.2023.10096505
Publikováno v:
Callanan, James, Garcia-Cabrera, Carles ORCID: 0000-0001-8139-9647 , Belton, Niamh ORCID: 0000-0003-4949-4745 , Roshchupkin, Gennady and Curran, Kathleen ORCID: 0000-0003-0095-9337 (2022) Integrating feature attribution methods into the loss function of deep learning classifiers. In: 24th Irish Machine Vision and Image Processing Conference, 31 Aug-2 Sept 2022, Belfast. ISBN 978-0-9934207-7-1
Feature attribution methods are typically used post-training to judge if a deep learning classifier is using meaningful concepts in an input image when making classifications. In this study, we propose using feature attribution methods to give a clas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4057bf1d601d18d4a9aa60f8fcfc23ea
http://doras.dcu.ie/27762/
http://doras.dcu.ie/27762/
Autor:
Niamh Belton, Aonghus Lawlor, Misgina Tsighe Hagos, Ivan Welaratne, Kathleen M. Curran, Adil Dahlan, Ronan T. Hearne
Publikováno v:
Medical Image Understanding and Analysis ISBN: 9783030804312
This work employs a pre-trained, multi-view Convolutional Neural Network (CNN) with a spatial attention block to optimise knee injury detection. An open-source Magnetic Resonance Imaging (MRI) data set with image-level labels was leveraged for this a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::870f1c90a470d524684d7cb5a2d1744a
https://doi.org/10.1007/978-3-030-80432-9_6
https://doi.org/10.1007/978-3-030-80432-9_6