Presentation information

Interactive Session

[3Rin4] Interactive 1

Thu. Jun 11, 2020 1:40 PM - 3:20 PM Room R01 (jsai2020online-2-33)

[3Rin4-58] Few-shot Learning with Data Augmentation with Generative Model.

Mu Zhou2,1, Yusuke Tanimura1,2, 〇Hidemoto Nakada1,2 (1.National Institute of Advanced Industrial Science and Technology,, 2.University of Tsukuba)

Keywords:One-shot Learning, Data Augumentation, Generative Model

While deep learning, in general, requires a large amount of labeled data,
there are situations where only a few samples are available for some classes.
In theory, if we can predict the probabilistic distribution of the classes
based on the samples for other classes, we can leverage the distribution to train the model.
We augment the data for the class with few samples using the generative model trained on the other classes for a classification task. We applied this method on MNIST dataset and
evaluate it.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.