Training Triplet Networks with GAN

04/06/2017
by   Maciej Zieba, et al.
0

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 FULL TEXT

page 1

page 2

page 3

page 4

research
02/24/2020

When Relation Networks meet GANs: Relation GANs with Triplet Loss

Though recent research has achieved remarkable progress in generating re...
research
03/24/2018

MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks

In this paper, we propose an enhanced triplet method that improves the e...
research
11/14/2017

TripletGAN: Training Generative Model with Triplet Loss

As an effective way of metric learning, triplet loss has been widely use...
research
01/24/2019

In Defense of the Triplet Loss for Visual Recognition

We employ triplet loss as a space embedding regularizer to boost classif...
research
06/11/2020

Training Generative Adversarial Networks with Limited Data

Training generative adversarial networks (GAN) using too little data typ...
research
11/28/2018

Semi-supervised learning with Bidirectional GANs

In this work we introduce a novel approach to train Bidirectional Genera...
research
07/29/2020

TR-GAN: Topology Ranking GAN with Triplet Loss for Retinal Artery/Vein Classification

Retinal artery/vein (A/V) classification lays the foundation for the qua...

Please sign up or login with your details

Forgot password? Click here to reset