Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Eric Arazo"'
Autor:
Yan, Sen, Zhu, Shaoshu, Fernandez, Jaime B., Sánchez, Eric Arazo, Gu, Yingqi, O'Connor, Noel E., O'Connor, David, Liu, Mingming
Pollution in urban areas can have significant adverse effects on the health and well-being of citizens, with traffic-related air pollution being a major concern in many cities. Pollutants emitted by vehicles, such as nitrogen oxides, carbon monoxide,
Externí odkaz:
http://arxiv.org/abs/2307.15401
Deep learning has shown excellent performance in analysing medical images. However, datasets are difficult to obtain due privacy issues, standardization problems, and lack of annotations. We address these problems by producing realistic synthetic ima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f4564bf683cf0f2370aa1828402c049
Publikováno v:
Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers ISBN: 9783031234422
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4084f213aacb6493efdb7bc542e4ad38
https://doi.org/10.1007/978-3-031-23443-9_36
https://doi.org/10.1007/978-3-031-23443-9_36
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198205
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4887134964b5a070aa4b36910a8e8d03
https://doi.org/10.1007/978-3-031-19821-2_23
https://doi.org/10.1007/978-3-031-19821-2_23
Publikováno v:
Ortego, Diego ORCID: 0000-0002-1011-3610 , Arazo, Eric, Albert, Paul, McGuinness, Kevin ORCID: 0000-0003-1336-6477 and O'Connor, Noel E. ORCID: 0000-0002-4033-9135 (2021) Multi-objective interpolation training for robustness to label noise. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 20-25 June 2021, Nashville, TN, USA + Virtual.
CVPR
CVPR
Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a Multi-Objec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f70d2b3424ffeacb4223e81b8534475
http://doras.dcu.ie/25597/
http://doras.dcu.ie/25597/
Publikováno v:
Eric, Arazo, Diego, Ortego ORCID: 0000-0002-1011-3610 , Paul, Albert, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 and Kevin, McGuinness ORCID: 0000-0003-1336-6477 (2021) How important is importance sampling for deep budgeted training? In: 32nd British Machine Vision Conference (BMVC) 2021, 22-25 Nov 2021, Virtual conference.
Long iterative training processes for Deep Neural Networks (DNNs) are commonly required to achieve state-of-the-art performance in many computer vision tasks. Importance sampling approaches might play a key role in budgeted training regimes, i.e. whe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______119::cb5c009618725ce0618b98f5e6271dc3
http://doras.dcu.ie/26408/
http://doras.dcu.ie/26408/
Publikováno v:
Albert, Paul, Ortego, Diego ORCID: 0000-0002-1011-3610 , Arazo, Eric, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 and McGuiness, Kevin ORCID: 0000-0003-1336-6477 (2021) ReLaB: reliable label bootstrapping for semi-supervised learning. In: International Joint Conference on Neural Networls (IJCNN), 18-22 July 2021, Shenzhen, China (Online).
IJCNN
IJCNN
Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reliable Label Bootstrapping (ReLaB), an unsupervised preprossessing algor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e30fc67c984dbd2134803b938708427
http://doras.dcu.ie/25767/
http://doras.dcu.ie/25767/
Publikováno v:
Ortego, Diego ORCID: 0000-0002-1011-3610 , Arazo, Eric, Albert, Paul, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 and McGuinness, Kevin ORCID: 0000-0003-1336-6477 (2021) Towards robust learning with different label noise distributions. In: International Conference on Pattern Recognition (ICPR) 2020, 10-15 Jan 2021, Milan, Italy (Online).
ICPR
ICPR
Noisy labels are an unavoidable consequence of labeling processes and detecting them is an important step towards preventing performance degradations in Convolutional Neural Networks. Discarding noisy labels avoids a harmful memorization, while the a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0fffda1be4ca0c4703f565ae911f677
http://doras.dcu.ie/25086/
http://doras.dcu.ie/25086/
Autor:
Juan C. SanMiguel, Kevin McGuinness, Eric Arazo, Noel E. O'Connor, Diego Ortego, José M. Martínez
Publikováno v:
CBMI
Ortego, Diego ORCID: 0000-0002-1011-3610, McGuinness, Kevin ORCID: 0000-0003-1336-6477 , SanMiguel, Juan C., Arazo, Eric, Martínez, José M. and O'Connor, Noel E. ORCID: 0000-0002-4033-9135 (2019) On guiding video object segmentation. In: International Conference on Content-Based Multimedia Indexing, 4-6 Sept 2019, Dublin, Ireland.
Ortego, Diego ORCID: 0000-0002-1011-3610
This paper presents a novel approach for segmenting moving objects in unconstrained environments using guided convolutional neural networks. This guiding process relies on foreground masks from independent algorithms (i.e. state-of-the-art algorithms
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::60f21c27a1e8f29a17002faaf7eeee42
http://arxiv.org/abs/1904.11256
http://arxiv.org/abs/1904.11256
Publikováno v:
Arazo Sánchez, Eric, Ortego, Diego ORCID: 0000-0002-1011-3610 , Albert, Paul, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 and McGuinness, Kevin ORCID: 0000-0003-1336-6477 (2020) Pseudo-labeling and confirmation bias in deep semi-supervised learning. In: 2020 International Joint Conference on Neural Networks, 19-24 July 2020, Glasgow, Scotland. ISBN 978-1-7281-6926-2
IJCNN
IJCNN
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from unlabeled samples
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b464ae3fe9e4ea111fe50a73c61680f8