The search functionality is under construction.
The search functionality is under construction.

Latent Space Virtual Adversarial Training for Supervised and Semi-Supervised Learning

Genki OSADA, Budrul AHSAN, Revoti PRASAD BORA, Takashi NISHIDE

  • Full Text Views

    0

  • Cite this

Summary :

Virtual Adversarial Training (VAT) has shown impressive results among recently developed regularization methods called consistency regularization. VAT utilizes adversarial samples, generated by injecting perturbation in the input space, for training and thereby enhances the generalization ability of a classifier. However, such adversarial samples can be generated only within a very small area around the input data point, which limits the adversarial effectiveness of such samples. To address this problem we propose LVAT (Latent space VAT), which injects perturbation in the latent space instead of the input space. LVAT can generate adversarial samples flexibly, resulting in more adverse effect and thus more effective regularization. The latent space is built by a generative model, and in this paper we examine two different type of models: variational auto-encoder and normalizing flow, specifically Glow. We evaluated the performance of our method in both supervised and semi-supervised learning scenarios for an image classification task using SVHN and CIFAR-10 datasets. In our evaluation, we found that our method outperforms VAT and other state-of-the-art methods.

Publication
IEICE TRANSACTIONS on Information Vol.E105-D No.3 pp.667-678
Publication Date
2022/03/01
Publicized
2021/12/09
Online ISSN
1745-1361
DOI
10.1587/transinf.2021EDP7161
Type of Manuscript
PAPER
Category
Artificial Intelligence, Data Mining

Authors

Genki OSADA
  Philips Co-Creation Center,University of Tsukuba,I Dragon Corporation
Budrul AHSAN
  Philips Co-Creation Center,The Tokyo Foundation for Policy Research
Revoti PRASAD BORA
  Lowe's Services India Pvt. Ltd.
Takashi NISHIDE
  University of Tsukuba

Keyword