Deep Clustering With Variational Autoencoder

Abstract

An autoencoder that learns a latent space in an unsupervised manner has many applications in signal processing. However, the latent space of an autoencoder does not pursue the same clustering goal as Kmeans or GMM. A recent work proposes to artificially re-align each point in the latent space of an autoencoder to its nearest class neighbors during training (Song et al. 2013). The resulting new latent space is found to be much more suitable for clustering, since clustering information is used. Inspired by previous works (Song et al . 2013), in this letter we propose several extensions to this technique. First, we propose a probabilistic approach to generalize Song's approach, such that Euclidean distance in the latent space is now represented by KL divergence. Second, as a consequence of this generalization we can now use probability distributions as inputs rather than points in the latent space. Third, we propose using Bayesian Gaussian mixture model for clustering in the latent space. We demonstrated our proposed method on digit recognition datasets, MNIST, USPS and SHVN as well as scene datasets, Scene15 and MIT67 with interesting findings.