Using Convolutional Neural Networks to Extract Shift-Invariant Features from Unlabeled Data

Abstract

Unsupervised learning on limited data is a challenging task. In this work, we show that shallow what-where autoencoders, first developed as a pretraining tool for supervised classifiers, can also be used for shift-invariant feature extraction. Furthermore, feature vectors (i.e., the bottleneck layer activations), can be clustered to achieve unsupervised segmentation. In order to remove edge artifacts in the segmentation, overcoding is introduced, whereby the decoder only needs to reproduce a cropped version of the encoded signal.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2019
Accession Number
AD1069298

Entities

People

  • Michael S. Lee
  • Samuel J. Edwards

Organizations

  • United States Army Research Laboratory

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Coding
  • Computer Languages
  • Computer Vision
  • Convolutional Neural Networks
  • Data Sets
  • Decoding
  • Dimensionality Reduction
  • Feature Extraction
  • Information Science
  • Machine Learning
  • Neural Networks
  • Signal Processing
  • Supervised Machine Learning
  • Two Dimensional
  • Unsupervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks