Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Michael Maire"'
Publikováno v:
Proceedings of the 44th International Conference on Software Engineering.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f88caa2a77ae503ec389fe3b448fe24c
https://doi.org/10.1145/3510003.3510068
https://doi.org/10.1145/3510003.3510068
Publikováno v:
Rejuvenation Research. 23:193-206
The ultrastructural effects of prolonged normothermic and cold ischemia on the cerebral cortex of the adult rat were investigated. Complete cerebral ischemia was produced by cardiac arrest and the animals' temperature was maintained at 37°C for peri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d425a989ef946f21c814f05907769080
https://doi.org/10.1089/rej.2019.2225
https://doi.org/10.1089/rej.2019.2225
Publikováno v:
ICSE
Machine learning (ML) cloud APIs enable developers to easily incorporate learning solutions into software systems. Unfortunately, ML APIs are challenging to use correctly and efficiently, given their unique semantics, data requirements, and accuracy-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50c714b8218ab38879b022c199a839d5
https://doi.org/10.1109/icse43902.2021.00024
https://doi.org/10.1109/icse43902.2021.00024
Publikováno v:
ICSE (Companion Volume)
This artifact aims to provide benchmark suite, data, and script used in our study "Are Machine Learning Cloud APIs Used Correctly?". We collected a suite of 360 non-trivial applications that use ML cloud APIs for manual study. We also developed check
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::538cd1402094ab6ece02c7433b4d1fe1
https://doi.org/10.1109/icse-companion52605.2021.00066
https://doi.org/10.1109/icse-companion52605.2021.00066
Autor:
Jianming Zhang, Baldo Faieta, Xin Yuan, Zhe Lin, Yilin Wang, Michael Maire, Jason Kuen, Ajinkya Gorakhnath Kale
Publikováno v:
CVPR
We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy prediction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66f0eaf1890a7aaeef4f52d5065ba12f
Publikováno v:
CVPR
The core of our approach, Pixel Consensus Voting, is a framework for instance segmentation based on the Generalized Hough transform. Pixels cast discretized, probabilistic votes for the likely regions that contain instance centroids. At the detected
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75f1bcc8b47a02b090615d46453df869
Publikováno v:
CVPR
We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d70014b3cc876dbba6404ae0e39e80d
Publikováno v:
CVPR
We construct custom regularization functions for use in supervised training of deep neural networks. Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an autoencoder ov
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cc9303074e838d56ae8d7fa6dc8db15
https://doi.org/10.1109/cvpr.2018.00590
https://doi.org/10.1109/cvpr.2018.00590
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012571
ECCV (12)
ECCV (12)
We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers. Such aggregation is critical to facilitate training of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9ec0ecec83939f8eccb5bd076b6a5cfe
https://doi.org/10.1007/978-3-030-01258-8_12
https://doi.org/10.1007/978-3-030-01258-8_12
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012519
ECCV (11)
ECCV (11)
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth (Strictly speaking, this statement is true only after one has compensated for camera rotation, individual object motion, and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d8c0edd63803f8946c407af7bac0478
https://doi.org/10.1007/978-3-030-01252-6_2
https://doi.org/10.1007/978-3-030-01252-6_2