Classification with Multiple Generative Adversaries

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Anagnostides, Ioannis, Theodoropoulos, Nikitas, Kasouridis, Stelios
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2020
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866901155435511808
author Anagnostides, Ioannis
Theodoropoulos, Nikitas
Kasouridis, Stelios
author_facet Anagnostides, Ioannis
Theodoropoulos, Nikitas
Kasouridis, Stelios
contents <p>In this work, we consider a natural extension of the two-player adversarial framework proposed by Goodfellow et al. (2014), specifically, in our setting a single discriminative network will compete against multiple generative networks, with each attempting to produce realistic samples from one of N distinct distributions. The objective of the Discriminator will be to classify every given input to one of 2N categories: N real classes and their fake counterparts. As a result, our adversarial paradigm is explicitly formulated in order to train the Discriminator to perform classification. We provide a theoretical analysis of our proposed architecture, deriving an expression for the optimal Discriminator and investigating the best response from the Generators - under optimal play. Moreover, through experimental results in MNIST we illustrate that our training method obtains strong performance with very limited training samples, outperforming the standard scheme for training Convolutional Neural Networks. Our empirical findings show that our model offers a compelling approach to prevent overfitting and circumscribe the generalization error, while at the same time the generative networks are able to produce samples with high perceptual score. The main caveat of our approach lies on the challenges of training in parallel multiple and competing neural networks.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18715409
institution Zenodo
language eng
publishDate 2020
publisher Zenodo
record_format zenodo
spellingShingle Classification with Multiple Generative Adversaries
Anagnostides, Ioannis
Theodoropoulos, Nikitas
Kasouridis, Stelios
Classification
Generative Models
Data Augmentation
Regularization
<p>In this work, we consider a natural extension of the two-player adversarial framework proposed by Goodfellow et al. (2014), specifically, in our setting a single discriminative network will compete against multiple generative networks, with each attempting to produce realistic samples from one of N distinct distributions. The objective of the Discriminator will be to classify every given input to one of 2N categories: N real classes and their fake counterparts. As a result, our adversarial paradigm is explicitly formulated in order to train the Discriminator to perform classification. We provide a theoretical analysis of our proposed architecture, deriving an expression for the optimal Discriminator and investigating the best response from the Generators - under optimal play. Moreover, through experimental results in MNIST we illustrate that our training method obtains strong performance with very limited training samples, outperforming the standard scheme for training Convolutional Neural Networks. Our empirical findings show that our model offers a compelling approach to prevent overfitting and circumscribe the generalization error, while at the same time the generative networks are able to produce samples with high perceptual score. The main caveat of our approach lies on the challenges of training in parallel multiple and competing neural networks.</p>
title Classification with Multiple Generative Adversaries
topic Classification
Generative Models
Data Augmentation
Regularization
url https://doi.org/10.5281/zenodo.18715409