Training Triplet Networks with GAN

Maciej Zieba, Lei Wang

Feb 17, 2017 (modified: Aug 23, 2017) ICLR 2017 workshop submission readers: everyone
  • 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.
  • Conflicts: pwr.edu.pl, uow.edu.au

Loading