Using convolutional neural network autoencoders to understand unlabeled data

Samuel Edwards; Michael S. Lee

doi:10.1117/12.2518459

10 May 2019 Using convolutional neural network autoencoders to understand unlabeled data

Samuel Edwards, Michael S. Lee

Proceedings Volume 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications; 1100618 (2019) https://doi.org/10.1117/12.2518459
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Gaining insight from unlabeled data is a widespread, challenging problem with many immediate applications. Clustering, dimensionality reduction for visualization, and anomaly detection are unsupervised learning solutions to this problem. Typically, the efficacy of these methods relies on obtaining sufficient amounts of data, presenting many challenges to cases where only limited data exists. In this work, we demonstrate that deep convolutional autoencoders can comfortably perform these tasks either directly or through manipulations of the latent space in a limited data setting. Clustering on common benchmark datasets produces comparable results to the current state-of-the-art in unsupervised classification. Clustering the activation maps of the encoding layers results in a form of unsupervised image segmentation with limited two-dimensional data. Visualizing the activation maps through dimension reduction demonstrates the possibilities of anomaly detection and semi-supervised learning. We are currently utilizing our versatile autoencoder to explore the ambitious task of finding anomalous and/or inconspicuous objects from single images.

Citation Download Citation

Samuel Edwards and Michael S. Lee "Using convolutional neural network autoencoders to understand unlabeled data", Proc. SPIE 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 1100618 (10 May 2019); https://doi.org/10.1117/12.2518459

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