Fast image scanning with deep max-pooling convolutional neural networks

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 o...

Full description

Saved in:
Bibliographic Details
Main Authors: Giusti, Alessandro, Ciresan, Dan C., Masci, Jonathan, Gambardella, Luca M., Schmidhuber, Jurgen
Format: Conference Proceeding
Language:English
Subjects:
Biomedical Imaging
Convolution
Deep Neural Networks
Detection
Forward-Propagation
Max-Pooling
Segmentation
Sliding Window
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2013.6738831