ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering

  • Ilia Sucholutsky
  • Matthias Schonlau

Abstract

While supervised learning techniques have become increasingly
adept at separating images into different classes, these techniques
require large amounts of labelled data which may not always be
available. We propose a novel neuro-dynamic method for unsuper-
vised image clustering by combining 2 biologically-motivated mod-
els: Adaptive Resonance Theory (ART) and Convolutional Neu-
ral Networks (CNN). ART networks are unsupervised clustering al-
gorithms that have high stability in preserving learned information
while quickly learning new information. Meanwhile, a major prop-
erty of CNNs is their translation and distortion invariance, which
has led to their success in the domain of vision problems. By
embedding convolutional layers into an ART network, the useful
properties of both networks can be leveraged to identify different
clusters within unlabelled image datasets and classify images into
these clusters. In exploratory experiments, we demonstrate that
this method greatly increases the performance of unsupervised
ART networks on a benchmark image dataset.

Published
2018-12-24
How to Cite
Sucholutsky, I., & Schonlau, M. (2018). ConvART: Improving Adaptive Resonance Theory for Unsupervised Image Clustering. Journal of Computational Vision and Imaging Systems, 4(1), 3. https://doi.org/10.15353/jcvis.v4i1.326