BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Talks.cam//talks.cam.ac.uk// X-WR-CALNAME:Talks.cam BEGIN:VEVENT SUMMARY:End-to-end learning of CNN features in in discrete optimization mo dels for motion and stereo - Thomas Pock (Graz University of Technology) DTSTART:20170907T085000Z DTEND:20170907T094000Z UID:TALK78221@talks.cam.ac.uk CONTACT:INI IT DESCRIPTION:Co-authors: Patrick Knö\;belreiter (Graz University of Technology)\, Alexander Shekhovtsov (Technical University of Prague)\ , Gottfried Munda (Graz University of Technology)\, Christian Reinbacher (Amazon)

For many years\, discrete optimization mod els such as conditional random fields (CRFs) have defined the state-of-the -art for classical correspondence problems such as motion and stereo. One of the most important ingredients in those models is the choice of the fea ture transform that is used to compute the similarity between images patch es. For a long time\, hand crafted features such as the celebrated scale invariant feature transform (SIFT) defined the state-of-the-art. Triggered by the recent success of convolutional neural networks (CNNs)\, it is qui te natural to learn such a feature transform from data. In this talk\, I w ill show how to efficiently learn such CNN features from data using an end -to-end learning approach. It turns out that our learned models yields sta te-of-the-art results on a number of established benchmark databases.
< br>Related Links

https:// arxiv.org/pdf/1707.06427 - Scalable Full Flow with Learned Binary Desc riptors
https://arxiv.or g/pdf/1611.10229 - End-to-End Training of Hybrid CNN-CRF Models for St ereo

LOCATION:Seminar Room 1\, Newton Institute END:VEVENT END:VCALENDAR