arxivst stuff from arxiv that you should probably bookmark

Training Triplet Networks with GAN

Abstract · Apr 6, 2017 17:09 ·

cs-lg stat-ml

Arxiv Abstract

  • Maciej Zieba
  • Lei Wang

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.

Read the paper (pdf) »