BYU

Abstract by David Kartchner

Personal Infomation


Presenter's Name

David Kartchner

Co-Presenters

Seth Glazier

Degree Level

Masters

Co-Authors

None

Abstract Infomation


Department

Computer Science

Faculty Advisor

Jeffrey Humpherys

Title

Deep Object Localization Transfer Learning for Automated Wildlife Monitoring

Abstract

Transfer learning has shown to meaningfully improve performance in multiple domains, including natural language processing, image recognition, and automated disease diagnosis.  We demonstrate the power of transfer learning from widely-used object localization datasets such as PASCAL 2012 and MS COCO on data collected from remote, automated wildlife monitoring stations operated by the United States Air Force.  We show that networks can quickly transfer knowledge learned from standard object detection tasks to quickly learn, recognize, and count never-before-seen objects.