Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/128217
Type: Conference paper
Title: Bayesian generative active deep learning
Author: Tran, T.M.
Do, T.-T.
Reid, I.
Carneiro, G.
Citation: Proceedings of Machine Learning Research, 2019 / Chaudhuri, K., Salakhutdinov, R. (ed./s), vol.97, pp.6295-6304
Publisher: PMLR
Issue Date: 2019
Series/Report no.: Proceedings of Machine Learning Research
ISBN: 9781510886988
ISSN: 2640-3498
Conference Name: 36th International Conference on Machine Learning (IMCL) (9 Jun 2019 - 15 Jun 2019 : Long Beach, CA, USA)
Editor: Chaudhuri, K.
Salakhutdinov, R.
Statement of
Responsibility: 
Toan Tran, Thanh-Toan Do, Ian Reid, Gustavo Carneiro
Abstract: Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled. Therefore, the design of effective training methods that require small labeled training sets is an important research direction that will allow a more effective use of resources. Among current approaches designed to address this issue, two are particularly interesting: data augmentation and active learning. Data augmentation achieves this goal by artificially generating new training points, while active learning relies on the selection of the “most informative” subset of unlabeled training samples to be labelled by an oracle. Although successful in practice, data augmentation can waste computational resources because it indiscriminately generates samples that are not guaranteed to be informative, and active learning selects a small subset of informative samples (from a large un-annotated set) that may be insufficient for the training process. In this paper, we propose a Bayesian generative active deep learning approach that combines active learning with data augmentation – we provide theoretical and empirical evidence (MNIST, CIFAR-{10,100}, and SVHN) that our approach has more efficient training and better classification results than data augmentation and active learning.
Rights: Copyright 2019 by the author(s).
Grant ID: http://purl.org/au-research/grants/arc/DP180103232
http://purl.org/au-research/grants/arc/CE140100016
http://purl.org/au-research/grants/arc/FL130100102
Published version: http://proceedings.mlr.press/v97/
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.