Fast image scanning with deep max-pooling convolutional neural networks

Alessandro Giusti; Dan C. Cireşan; Jonathan Masci; Luca M. Gambardella; Jürgen Schmidhuber

doi:10.1109/ICIP.2013.6738831

Fast image scanning with deep max-pooling convolutional neural networks

Alessandro Giusti, Dan C. Cireşan, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

244 Scopus citations

Abstract

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. © 2013 IEEE.

Original language	English (US)
Title of host publication	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Publisher	IEEE Computer Society
Pages	4034-4038
Number of pages	5
ISBN (Print)	9781479923410
DOIs	https://doi.org/10.1109/ICIP.2013.6738831
State	Published - Jan 1 2013
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14

Access to Document

10.1109/ICIP.2013.6738831

Cite this

@inproceedings{ebfc52c8ca844dbfa8e7b7d7eae6c13c,

title = "Fast image scanning with deep max-pooling convolutional neural networks",

abstract = "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. {\textcopyright} 2013 IEEE.",

author = "Alessandro Giusti and Cire{\c s}an, {Dan C.} and Jonathan Masci and Gambardella, {Luca M.} and J{\"u}rgen Schmidhuber",

note = "Generated from Scopus record by KAUST IRTS on 2022-09-14",

year = "2013",

month = jan,

day = "1",

doi = "10.1109/ICIP.2013.6738831",

language = "English (US)",

isbn = "9781479923410",

pages = "4034--4038",

booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

publisher = "IEEE Computer Society",

address = "United States",

}

TY - GEN

T1 - Fast image scanning with deep max-pooling convolutional neural networks

AU - Giusti, Alessandro

AU - Cireşan, Dan C.

AU - Masci, Jonathan

AU - Gambardella, Luca M.

AU - Schmidhuber, Jürgen

N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14

PY - 2013/1/1

Y1 - 2013/1/1

N2 - 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. © 2013 IEEE.

AB - 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. © 2013 IEEE.

UR - http://ieeexplore.ieee.org/document/6738831/

UR - http://www.scopus.com/inward/record.url?scp=84897769461&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738831

DO - 10.1109/ICIP.2013.6738831

M3 - Conference contribution

SN - 9781479923410

SP - 4034

EP - 4038

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

PB - IEEE Computer Society

ER -

Fast image scanning with deep max-pooling convolutional neural networks

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this