Generative approach to unsupervised deep local learning

Changlu Chen; Chaoxi Niu; Xia Zhan; Kun Zhan

doi:10.1117/1.JEI.28.4.043005

10 July 2019 Generative approach to unsupervised deep local learning

Changlu Chen, Chaoxi Niu, Xia Zhan, Kun Zhan

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 4, 043005 (July 2019). https://doi.org/10.1117/1.JEI.28.4.043005

Abstract

Most existing feature learning methods optimize inflexible handcrafted features and the affinity matrix is constructed by shallow linear embedding methods. Different from these conventional methods, we pretrain a generative neural network by stacking convolutional autoencoders to learn the latent data representation and then construct an affinity graph with them as a prior. Based on the pretrained model and the constructed graph, we add a self-expressive layer to complete the generative model and then fine-tune it with a new loss function, including the reconstruction loss and a deliberately defined locality-preserving loss. The locality-preserving loss designed by the constructed affinity graph serves as prior to preserve the local structure during the fine-tuning stage, which in turn improves the quality of feature representation effectively. Furthermore, the self-expressive layer between the encoder and the decoder is based on the assumption that each latent feature is a linear combination of other latent features, so the weighted combination coefficients of the self-expressive layer are used to construct a new refined affinity graph for representing the data structure. We conduct experiments on four datasets to demonstrate the superiority of the representation ability of our proposed model over the state-of-the-art methods.

Citation Download Citation

Changlu Chen, Chaoxi Niu, Xia Zhan, and Kun Zhan "Generative approach to unsupervised deep local learning," Journal of Electronic Imaging 28(4), 043005 (10 July 2019). https://doi.org/10.1117/1.JEI.28.4.043005

Received: 22 February 2019; Accepted: 18 June 2019; Published: 10 July 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available