Fast image scanning with deep max-pooling convolutional neural networks
- 1 September 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 4034-4038
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.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Multi-column deep neural networks for image classification2012
- Large-Scale FPGA-Based Convolutional Networks2011
- The German Traffic Sign Recognition Benchmark: A multi-class classification competition2011
- Deep, Big, Simple Neural Nets for Handwritten Digit RecognitionNeural Computation, 2010
- An Integrated Micro- and Macroarchitectural Analysis of the Drosophila Brain by Computer-Assisted Serial Section Electron MicroscopyPLOS Biology, 2010
- Chinese Handwriting Recognition Contest 20102010
- An FPGA-based stream processor for embedded real-time vision with Convolutional Networks2009
- Best practices for convolutional neural networks applied to visual document analysis2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980