Training Triplet Networks with GAN

2017/04/06 by Maciej Zieba, Lei Wang, Zieba, Maciej +1
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1704.02227

arxiv created 2017/04/06 · arxiv updated 2017/04/10

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.

Related

• A Three-Player GAN: Generating Hard Samples To Improve Classification Networks
• MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators
• Triple Generative Adversarial Nets
• Data Augmentation Using GANs
• Improved Techniques for Training GANs