Share Email Print
cover

Proceedings Paper • new

Using convolutional neural network autoencoders to understand unlabeled data
Author(s): Samuel Edwards; Michael S. Lee
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 10 May 2019
PDF: 15 pages
Proc. SPIE 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 1100618 (10 May 2019); doi: 10.1117/12.2518459
Show Author Affiliations
Samuel Edwards, U.S. Army Research Lab. (United States)
Parsons Corp. (United States)
Michael S. Lee, U.S. Army Research Lab. (United States)


Published in SPIE Proceedings Vol. 11006:
Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications
Tien Pham, Editor(s)

© SPIE. Terms of Use
Back to Top