Beyond one-hot encoding: Lower dimensional target embedding

Pau Rodríguez, Miguel A. Bautista, Jordi Gonzàlez, Sergio Escalera

Research output: Contribution to journalArticleResearchpeer-review

37 Citations (Scopus)

Abstract

© 2018 Elsevier B.V. Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, one-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy. Our contribution is two fold: (i) We show that random projections of the label space are a valid tool to find such lower dimensional embeddings, boosting dramatically convergence rates at zero computational cost; and (ii) we propose a normalized eigenrepresentation of the class manifold that encodes the targets with minimal information loss, improving the accuracy of random projections encoding while enjoying the same convergence rates. Experiments on CIFAR-100, CUB200-2011, Imagenet, and MIT Places demonstrate that the proposed approach drastically improves convergence speed while reaching very competitive accuracy rates.
Original languageEnglish
Pages (from-to)21-31
JournalImage and Vision Computing
Volume75
DOIs
Publication statusPublished - 1 Jul 2018

Keywords

  • Computer vision
  • Deep learning
  • Error correcting output codes
  • Output embeddings

Fingerprint Dive into the research topics of 'Beyond one-hot encoding: Lower dimensional target embedding'. Together they form a unique fingerprint.

Cite this