Adapting representations from a source domain to instances from a new target domain is an important problem in machine learning. In this work, the method of unsupervised domain adaptation in the context of mine countermeasure and automated target recognition is presented, where we have labeled data only from the source domain. Motivated by incremental learning, we create intermediate representations of data between the two domains and utilize this information to create new datasets.

This presentation is part of Minisymposium “MS3 - Applications of Imaging Modalities beyond the Visible Spectrum (2 parts)”
organized by: Max Gunzburger (Florida State University) , G-Michael Tesfaye (Naval Surface Warfare Center, Panama City) , Janet Peterson (Florida State University) .

Authors:

Jason C. Isaacs (Naval Surface Weapons Center - Panama City)

Keywords:

automated target detection, incremental learning, machine learning, unsupervised learning