Zobrazeno 1 - 10
of 328
pro vyhledávání: '"Stefano Soatto"'
Publikováno v:
Entropy, Vol 23, Iss 7, p 922 (2021)
We introduce the Redundant Information Neural Estimator (RINE), a method that allows efficient estimation for the component of information about a target variable that is common to a set of sources, known as the “redundant information”. We show t
Externí odkaz:
https://doaj.org/article/42dc337b4d4545ac8b4134b23d2948b2
Publikováno v:
Entropy, Vol 22, Iss 1, p 101 (2020)
This paper is a step towards developing a geometric understanding of a popular algorithm for training deep neural networks named stochastic gradient descent (SGD). We built upon a recent result which observed that the noise in SGD while training typi
Externí odkaz:
https://doaj.org/article/21d83ed6dd34421083c9cbde1cc87a9e
Autor:
Mingqi Han, Eric A. Bushong, Mayuko Segawa, Alexandre Tiard, Alex Wong, Morgan R. Brady, Milica Momcilovic, Dane M. Wolf, Ralph Zhang, Anton Petcherski, Matthew Madany, Shili Xu, Jason T. Lee, Masha V. Poyurovsky, Kellen Olszewski, Travis Holloway, Adrian Gomez, Maie St. John, Steven M. Dubinett, Carla M. Koehler, Orian S. Shirihai, Linsey Stiles, Aaron Lisberg, Stefano Soatto, Saman Sadeghi, Mark H. Ellisman, David B. Shackelford
Publikováno v:
Nature, vol 615, iss 7953
Acknowledgements: We thank C. Zamilpa, D. Abeydeera and J. Collins, at UCLA’s Crump Imaging Technology Center, for assistance with PET–CT imaging of the mice. We thank the Translational Pathology Core Laboratory at UCLA’s DGSOM for assistance w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25ba0e060fdb5e0999dce8457473be4c
Publikováno v:
Neural Networks. 139:348-357
We present a stochastic first-order optimization algorithm, named block-cyclic stochastic coordinate descent (BCSC), that adds a cyclic constraint to stochastic block-coordinate descent in the selection of both data and parameters. It uses different
Publikováno v:
IEEE Robotics and Automation Letters. 6:3120-3127
We present a method to infer a dense depth map from a color image and associated sparse depth measurements. Our main contribution lies in the design of an annealing process for determining co-visibility (occlusions, disocclusions) and the degree of r
Autor:
Pei Wang, Zhaowei Cai, Hao Yang, Gurumurthy Swaminathan, Nuno Vasconcelos, Bernt Schiele, Stefano Soatto
Publikováno v:
IEEE/CVF Conference on Computer Vision and Pattern Recognition
We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture, Omni-DETR,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cede7892bcd7ba37b64ba23cc705473a
http://arxiv.org/abs/2203.16089
http://arxiv.org/abs/2203.16089
Autor:
Zhaowei Cai, Gukyeong Kwon, Avinash Ravichandran, Erhan Bas, Zhuowen Tu, Rahul Bhotika, Stefano Soatto
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200588
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb57ff6486d1fc396ff9335deef64781
https://doi.org/10.1007/978-3-031-20059-5_17
https://doi.org/10.1007/978-3-031-20059-5_17
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
Autor:
Yunhao Ba, Howard Zhang, Ethan Yang, Akira Suzuki, Arnold Pfahnl, Chethan Chinder Chandrappa, Celso M. de Melo, Suya You, Stefano Soatto, Alex Wong, Achuta Kadambi
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200700
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::48f0a9df03b8f4962241f7293c427760
https://doi.org/10.1007/978-3-031-20071-7_42
https://doi.org/10.1007/978-3-031-20071-7_42
Autor:
Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto
We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong differential priva
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d61a32561946f4362f02ff0bf57bebc