PDF-Scene Parsing with Multiscale Feature Learning Purity Trees and Optimal Covers Clment Farabet CFARABET CS NYU EDU Camille Couprie CCOUPRIE CS NYU EDU Laurent Najman NAJMAN ESIEE FR Yann LeCun YANN CS
We propose a method that uses a mul tiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes
Download Presentation
"Scene Parsing with Multiscale Feature Learning Purity Trees " is the property of its rightful owner. Permission is granted to download and print materials on this website for personal, non-commercial use only, provided you retain all copyright notices. By downloading content from our website, you accept the terms of this agreement.
Presentation Transcript
Transcript not available.