Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks

Alessandro Giusti, Dan C. Ciresan, Jonathan Masci, Luca M. Gambardella, Jurgen Schmidhuber
IDSIA / USI-SUPSI, Dalle Molle Institute for Artificial Intelligence, Galleria 2, 6928 Manno, Switzerland
arXiv:1302.1700 [cs.CV], (7 Feb 2013)


   author={Giusti}, A. and {Cire{c s}an}, D.~C. and {Masci}, J. and {Gambardella}, L.~M. and {Schmidhuber}, J.},

   title={"{Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks}"},

   journal={ArXiv e-prints},




   keywords={Computer Science – Computer Vision and Pattern Recognition, Computer Science – Artificial Intelligence},




   adsnote={Provided by the SAO/NASA Astrophysics Data System}


Download Download (PDF)   View View   Source Source   



Deep Neural Networks now excel at image classification, detection and segmentation. When used to scan images by means of a sliding window, however, their high computational complexity can bring even the most powerful hardware to its knees. We show how dynamic programming can speedup the process by orders of magnitude, even when max-pooling layers are present.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: