Share Email Print
cover

Proceedings Paper • new

Initial investigation into the effect of image degradation on the performance of a 3-category classifier using transfer learning and data augmentation
Author(s): Keith D. Anthony; Brett J. Borghetti; Bryan J. Steward
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper documents an initial investigation into the effect of image degradation on the performance of transfer learning (TL) as the number of retrained layers is varied, using a well-documented, commonly-used, and well- performing deep learning classifier (VGG16). Degradations were performed on a publicly-available data set to simulate the effects of noise and varying optical resolution by electro-optical (EO/IR) imaging sensors. Performance measurements were gathered on TL performance on the base image-set as well as modified image-sets with different numbers of retrained layers, with and without data augmentation. It is shown that TL mitigates against corrupt data, and improves classifier performance with increased numbers of retrained layers. Data augmentation also improves performance. At the same time, the phenomenal performance of TL cannot overcome the lack of feature information in severely degraded images. This experiment provides a qualitative sense of when transfer learning cannot be expected to improve classification results.

Paper Details

Date Published: 14 May 2019
PDF: 18 pages
Proc. SPIE 10986, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV, 109860R (14 May 2019); doi: 10.1117/12.2519019
Show Author Affiliations
Keith D. Anthony, Air Force Institute of Technology (United States)
Brett J. Borghetti, Air Force Institute of Technology (United States)
Bryan J. Steward, Air Force Institute of Technology (United States)


Published in SPIE Proceedings Vol. 10986:
Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV
Miguel Velez-Reyes; David W. Messinger, Editor(s)

© SPIE. Terms of Use
Back to Top