Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Daniel Sedra"'
Publikováno v:
Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 4:239-248
Scene understanding algorithms in computer vision are improving dramatically by training deep convolutional neural networks on millions of accurately annotated images. Collecting large-scale datasets for this kind of training is challenging, and the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4734efea8f419ca3ae0737f1d240fcd8
https://doi.org/10.1609/hcomp.v4i1.13293
https://doi.org/10.1609/hcomp.v4i1.13293
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464923
ECCV (4)
ECCV (4)
Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87801165ea1d5f2f0780db465bb3ea7a
https://doi.org/10.1007/978-3-319-46493-0_39
https://doi.org/10.1007/978-3-319-46493-0_39
