DATA-EFFICIENT LEARNING BY ADVERSARIAL DISCRIMINATIVE DOMAIN ADAPTATION

Abstract

The goal of this effort was to streamlined the end-to-end process of using machine learning for AF/DoD tasks. Focusing on domain adaptation, University of California at Berkeley developed a discriminatively-trained Cycle-Consistent Adversarial Domain Adaptation model, a Semantic Pixel-Level Adaptation Transform approach to detector adaptation that efficiently generates cross-domain image pairs, and an adaptation method that exploits the continuity between gradually varying domains by adapting in sequence from the source to the most similar target domain. The models can be applied in a variety of visual recognition and prediction settings. They show new state-of-the-art results across multiple adaptation tasks.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 04, 2020
Accession Number
AD1090716

Entities

People

  • Trevor Darrell

Organizations

  • University of California Regents

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Artificial Intelligence Software
  • Bayesian Networks
  • Computational Science
  • Computer Vision
  • Computers
  • Convolutional Neural Networks
  • Cross Domain
  • Detectors
  • Information Processing
  • Information Science
  • Information Systems
  • Machine Learning
  • Neural Networks
  • Pattern Recognition
  • Recognition

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks