BibTex format
@unpublished{Wang:2017,
author = {Wang, R and Cully, A and Chang, HJ and Demiris, Y},
title = {MAGAN: Margin Adaptation for Generative Adversarial Networks},
url = {http://arxiv.org/abs/1704.03817v3},
year = {2017}
}
Publications
Citation
RIS format (EndNote, RefMan)
TY - UNPB
AB - We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs)algorithm, a novel training procedure for GANs to improve stability andperformance by using an adaptive hinge loss function. We estimate theappropriate hinge loss margin with the expected energy of the targetdistribution, and derive principled criteria for when to update the margin. Weprove that our method converges to its global optimum under certainassumptions. Evaluated on the task of unsupervised image generation, theproposed training procedure is simple yet robust on a diverse set of data, andachieves qualitative and quantitative improvements compared to thestate-of-the-art.
AU - Wang,R
AU - Cully,A
AU - Chang,HJ
AU - Demiris,Y
PY - 2017///
TI - MAGAN: Margin Adaptation for Generative Adversarial Networks
UR - http://arxiv.org/abs/1704.03817v3
ER -