Please use this identifier to cite or link to this item:
Title: Denoising auto-encoders toward robust unsupervised feature representation
Authors: Xiong, W
Du, B
Zhang, L
Zhang, L
Tao, D
Issue Date: 2016
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Proceedings of the International Joint Conference on Neural Networks, 2016, v. 2016-October, 7727820, p. 4721-4728 How to cite?
Abstract: Deep networks like the convolutional neural network and its variants usually learn hierarchical features from labeled images, which is very expensive to obtain. How can we find an unsupervised way to effectively extract deep and abstract features from images without annotations? Even from large qualities of images with noise? In this paper, we propose a robust deep neural network, named as stacked convolutional denoising auto-encoders (SCDAE), which can map raw images to hierarchical representations in an unsupervised manner. Our network is elaborately designed to fit for the visual recognition tasks. It is established by stacking the denoising auto-encoders. Unlike the prior works, in the training phase, the auto-encoders are trained patch-wisely so that the latent features can be applied to powerful regularizers for better representation; in the inference phase, the denoising auto-encoders are stacked convolutionally, hence the generated feature maps in the higher layers can preserve the coherent structures within the features in the lower layers. To achieve better performance, we apply whitening to each layer to sphere the input features. Our network is evaluated on the challenging image datasets MNIST, CIFAR-10 and STL-10 and demonstrates superior performance to the state-of-the-art unsupervised networks.
Description: 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, Canada, 24-29 July 2016
ISBN: 9781509006199
DOI: 10.1109/IJCNN.2016.7727820
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Feb 22, 2019

Page view(s)

Last Week
Last month
Citations as of Feb 17, 2019

Google ScholarTM



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