Active Adversarial Domain Adaptation
WACV 2020 | We propose an active learning approach for transferring representations across domains. Active adversarial domain adaptation (AADA) explores a duality between two related problems: (i) adversarial domain alignment and (ii) importance sampling for adapting models across domains. The former uses a domain-discriminative model to align domains, while the latter utilizes it to weigh samples to account for distribution shifts. Our importance weight promotes samples with large uncertainty in classification and diversity from labeled examples, thus serving as a sample selection scheme for active learning.