Convolutional Clustering for Unsupervised Learning

TL;DR

This paper introduces a convolutional k-means clustering method for unsupervised learning in deep neural networks, reducing the need for labeled data and improving accuracy on benchmark datasets.

Contribution

It proposes an enhanced convolutional k-means algorithm that reduces parameter correlation and improves unsupervised feature learning in deep networks.

Findings

Achieved 74.1% accuracy on STL-10

Obtained 0.5% error on MNIST

Outperformed other unsupervised filter learning techniques

Abstract

The task of labeling data for training deep neural networks is daunting and tedious, requiring millions of labels to achieve the current state-of-the-art results. Such reliance on large amounts of labeled data can be relaxed by exploiting hierarchical features via unsupervised learning techniques. In this work, we propose to train a deep convolutional network based on an enhanced version of the k-means clustering algorithm, which reduces the number of correlated parameters in the form of similar filters, and thus increases test categorization accuracy. We call our algorithm convolutional k-means clustering. We further show that learning the connection between the layers of a deep convolutional neural network improves its ability to be trained on a smaller amount of labeled data. Our experiments show that the proposed algorithm outperforms other techniques that learn filters unsupervised. Specifically, we obtained a test accuracy of 74.1% on STL-10 and a test error of 0.5% on MNIST.