Virtual Adversarial Training : A Regularization Method for Supervised and Semi-Supervised Learning

We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local pertur...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 41(2019), 8 vom: 24. Aug., Seite 1979-1993
1. Verfasser:	Miyato, Takeru (VerfasserIn)
Weitere Verfasser:	Maeda, Shin-Ichi, Koyama, Masanori, Ishii, Shin
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2019
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article