papers AI Learner
The Github is limit! Click to go to the new site.

Semi-supervised learning with Bidirectional GANs

2018-11-28
Maciej Zamorski, Maciej Zięba

Abstract

In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner. The presented method utilizes triplet loss function as an additional component of the objective function used to train discriminative data representation in the latent space of the BiGAN model. This representation can be further used as a seed for generating artificial images, but also as a good feature embedding for classification and image retrieval tasks. We evaluate the quality of the proposed method in the two mentioned challenging tasks using two benchmark datasets: CIFAR10 and SVHN.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1811.11426

PDF

https://arxiv.org/pdf/1811.11426


Similar Posts

Comments