Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Safa Cicek"'
Autor:
Alex Wong, Allison Chen, Yangchao Wu, Safa Cicek, Alexandre Tiard, Byung-Woo Hong, Stefano Soatto
Publikováno v:
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries ISBN: 9783031089985
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21e640a7b41919ea5503b36075a26a53
https://doi.org/10.1007/978-3-031-08999-2_6
https://doi.org/10.1007/978-3-031-08999-2_6
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695347
ACCV (3)
ACCV (3)
We propose a method for semantic segmentation in the unsupervised domain adaptation (UDA) setting. We particularly examine the domain gap between spatial-class distributions and propose to align the local distributions of the segmentation predictions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33848aa04ce6775c68496d0c6ca01df2
https://doi.org/10.1007/978-3-030-69535-4_38
https://doi.org/10.1007/978-3-030-69535-4_38
We present a method for inferring dense depth maps from images and sparse depth measurements by leveraging synthetic data to learn the association of sparse point clouds with dense natural shapes, and using the image as evidence to validate the predi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2e188e8b2868fa918189cd9324488b6
Autor:
Stefano Soatto, Safa Cicek
Publikováno v:
ICCV Workshops
We propose regularizing the empirical loss for semi-supervised learning by acting on both the input (data) space, and the weight (parameter) space. We show that the two are not equivalent, and in fact are complementary, one affecting the minimality o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a96ff1d687cea90708b4ddd01b7d0a0
https://doi.org/10.1109/iccvw.2019.00170
https://doi.org/10.1109/iccvw.2019.00170
Autor:
Safa Cicek, Stefano Soatto
Publikováno v:
ICCV
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ad84fd0f1ce32060a7eb604a7205db8
https://doi.org/10.1109/iccv.2019.00150
https://doi.org/10.1109/iccv.2019.00150
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012151
ECCV (2)
ECCV (2)
We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown labels. Traini
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6fe503cabb87345a3d34a0e571077c91
https://doi.org/10.1007/978-3-030-01216-8_10
https://doi.org/10.1007/978-3-030-01216-8_10