Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Kamnitsas K"'
Publikováno v:
Scopus-Elsevier
Daniel Coelho de Castro
Neural Information Processing Systems (NeurIPS)
Daniel Coelho de Castro
Neural Information Processing Systems (NeurIPS)
Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data such that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ca4fe55dcf93a6671e5a8ac2802b546
Autor:
Kamnitsas, K., Castro, D. C., Loïc Le Folgoc, Walker, I., Tanno, R., Rueckert, D., Glocker, B., Criminisi, A., Nori, A.
Publikováno v:
International Conference on Machine Learning (ICML) 2018
Daniel Coelho de Castro
Scopus-Elsevier
Daniel Coelho de Castro
Scopus-Elsevier
We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation. The key idea is to dynamically create a graph over embeddings of labeled and unlabeled s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ace858418944f3a0cc78f076c7acc42b
http://arxiv.org/abs/1806.02679
http://arxiv.org/abs/1806.02679
Autor:
Oktay, O, Ferrante, E, Kamnitsas, K, Heinrich, M, Bai, W, Caballero, J, Cook, S, De Marvao, A, Dawes, T, O'Regan, D, Kainz, B, Glocker, B, Rueckert, D
Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acqu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f86c36bb2950a62c57526fe92013927b
Autor:
Monteiro, M., Loïc Le Folgoc, Castro, D. C., Pawlowski, N., Marques, B., Kamnitsas, K., Wilk, M., Glocker, B.
Publikováno v:
Scopus-Elsevier
Daniel Coelho de Castro
Daniel Coelho de Castro
In image segmentation, there is often more than one plausible solution for a given input. In medical imaging, for example, experts will often disagree about the exact location of object boundaries. Estimating this inherent uncertainty and predicting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c0b7b0c7bfd33df2ddb0bfe303f73be4
http://www.scopus.com/inward/record.url?eid=2-s2.0-85104287606&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85104287606&partnerID=MN8TOARS