K-Autoencoders Deep Clustering

Yaniv Opochinsky, Shlomo E. Chazan, Sharon Gannot, Jacob GoldbergerICASSP 2020 · OpenReview

Abstract

In this study we propose a deep clustering algorithm that extends the k-means algorithm. Each cluster is represented by an autoencoder instead of a single centroid vector. Each data point is associated with the autoencoder which yields the minimal reconstruction error. The optimal clustering is found by learning a set of autoencoders that minimize the global reconstruction mean-square error loss. The network architecture is a simplified version of a previous method that is based on mixture-of-experts. The proposed method is evaluated on standard image corpora and performs on par with state-of-the-art methods which are based on much more complicated network architectures.
BibTeX
@inproceedings{opochinsky2020k,
  author = {Yaniv Opochinsky and Shlomo E. Chazan and Sharon Gannot and Jacob Goldberger},
  title = {{K-Autoencoders Deep Clustering}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  url = {https://openreview.net/forum?id=QR93Fj2jl4i},
}

Loading related content...

Figure