Skip to main content
placeholder image

Training triplet networks with GaN

Conference Paper


Abstract


  • Triplet networks are widely used models that are characterized by good performance in classification and retrieval tasks. In this work we propose to train a triplet network by putting it as the discriminator in Generative Adversarial Nets (GANs). We make use of the good capability of representation learning of the discriminator to increase the predictive quality of the model. We evaluated our approach on Cifar10 and MNIST datasets and observed significant improvement on the classification performance using the simple k-nn method.

Authors


  •   Zieba, Maciej M. (external author)
  •   Wang, Lei

Publication Date


  • 2017

Citation


  • Zieba, M. & Wang, L. (2017). Training triplet networks with GaN. 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings (pp. 1-6).

Scopus Eid


  • 2-s2.0-85071127281

Start Page


  • 1

End Page


  • 6

Abstract


  • Triplet networks are widely used models that are characterized by good performance in classification and retrieval tasks. In this work we propose to train a triplet network by putting it as the discriminator in Generative Adversarial Nets (GANs). We make use of the good capability of representation learning of the discriminator to increase the predictive quality of the model. We evaluated our approach on Cifar10 and MNIST datasets and observed significant improvement on the classification performance using the simple k-nn method.

Authors


  •   Zieba, Maciej M. (external author)
  •   Wang, Lei

Publication Date


  • 2017

Citation


  • Zieba, M. & Wang, L. (2017). Training triplet networks with GaN. 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings (pp. 1-6).

Scopus Eid


  • 2-s2.0-85071127281

Start Page


  • 1

End Page


  • 6