Adaptation Across Extreme Variations using Unlabeled Bridges
BMCV 2020 | We tackle an unsupervised domain adaptation problem: when the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter- and intra-domain variation. We propose decomposing domain discrepancy into multiple smaller discrepancies by introducing unlabeled bridging domains that connect the source and target domains; this makes it easier to minimize each. We implement our proposed approach through an extension of the domain adversarial neural network with multiple discriminators, each of which accounts for reducing discrepancies between unlabeled (bridge, target) domains and a mix of all precedent domains, including source.
Collaborators: Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin, Manmohan Chandraker