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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 04, 2020
- Accession Number
- AD1090716
Entities
People
- Trevor Darrell
Organizations
- University of California Regents