AI summary

This paper introduces a convolutional neural network (ConvNet) architecture that uses multi-stage features and Lp pooling, achieving a state-of-the-art accuracy of 94.85% on the SVHN dataset, and analyzes the benefits of different pooling methods and multi-stage features in ConvNets.

Abstract

We classify digits of real-world house numbers using convolutional neural networks (ConvNets). ConvNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 94.85% accuracy on the SVHN dataset (45.2% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.