Spatially-sparse convolutional neural networks

TL;DR

This paper introduces a spatially-sparse CNN architecture that efficiently processes sparse inputs, significantly improving training efficiency and accuracy on handwriting recognition and image classification tasks.

Contribution

The paper presents a novel CNN design that leverages input sparsity to enhance training efficiency and accuracy on sparse and dense datasets.

Findings

Achieved 3.82% error on CASIA-OLHWDB1.1 handwriting dataset.

Reduced test error to 6.28% on CIFAR-10.

Reduced test error to 24.30% on CIFAR-100.

Abstract

Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification. However, the performance of the networks is often limited by budget and time constraints, particularly when trying to train deep networks. Motivated by the problem of online handwriting recognition, we developed a CNN for processing spatially-sparse inputs; a character drawn with a one-pixel wide pen on a high resolution grid looks like a sparse matrix. Taking advantage of the sparsity allowed us more efficiently to train and test large, deep CNNs. On the CASIA-OLHWDB1.1 dataset containing 3755 character classes we get a test error of 3.82%. Although pictures are not sparse, they can be thought of as sparse by adding padding. Applying a deep convolutional network using sparsity has resulted in a substantial reduction in test error on the CIFAR small picture datasets: 6.28% on CIFAR-10 and 24.30% for CIFAR-100.