You are here

Low-shot Automated Performance Prediction via Transfer Learning

Award Information
Agency: Department of Defense
Branch: National Geospatial-Intelligence Agency
Contract: HM047621C0029
Agency Tracking Number: NGA-P1-21-01
Amount: $99,866.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: NGA20C-001
Solicitation Number: 20.C
Solicitation Year: 2020
Award Year: 2021
Award Start Date (Proposal Award Date): 2021-04-19
Award End Date (Contract End Date): 2022-02-02
Small Business Information
5050 Section Avenue Suite 110
Cincinnati, OH 45212-1111
United States
DUNS: 964730451
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 George Goley
 (937) 660-4302
Business Contact
 Elizabeth McPheron
Phone: (937) 531-0425
Research Institution
 Michigan Technological University
 Carol Wiitanen
Lakeshore Center 1400 Townsend Drive
Houghton, MI 49931-1295
United States

 (906) 487-2226
 Nonprofit College or University

Low-shot objection recognition has become an area of active research in recent years, with advances dramatically improving performance when only a few samples are available, nominally fewer than 20. These technologies are a focus of the intelligence community (IC) because this challenge pertains to many intelligence problems, e.g., objects of interest are rare due to their use, sensitive nature, or context.  Published works artificially subsample a class to create a low-shot environment in training and retain the larger sample size for the test environment; however, how do we determine performance when only a few samples truly exist? The traditional cross-validation approach with training/test separation breaks down when only a few exemplars are available. This problem is further exacerbated by correlation amongst the example images (e.g., derived from the same location, time, relative aspect, etc.).  Furthermore, traditional approaches do not provide either performance estimates or an indication of uncertainty (especially relevant measures given the limited training data).  Without an understanding of the performance of such a system, it's impossible to abide by the DoD ethical principles of Artificial Intelligence. \n\n Our proposed Low-shot Transfer Performance Predictor (LowTraPP) first models the performance of well-sampled classes, a process that is agnostic to the underlying recognition system.  The resulting learned distributions then serve as priors for modeling low-shot classes' performance as a function of critical operating parameters. LowTraPP satisfies the following requirements levied by the IC community: \n\n\n\t LowTraPP is agnostic to the recognition system \n\t LowTraPP provides an estimate of performance with confidence bounds \n\t LowTraPP is a function of operating conditions of interest \n\t LowTraPP operates solely on available measured data  \n

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government