Abstract. Domain adaptation is an important tool to transfer knowledge about a task (e.g. classification) learned in a source domain to a
second, or target domain. Current approaches assume that task-relevant
target-domain data is available during training. We demonstrate how to
perform domain adaptation when no such task-relevant target-domain
data is available. To tackle this issue, we propose zero-shot deep domain adaptation (ZDDA), which uses privileged information from taskirrelevant dual-domain pairs. ZDDA learns a source-domain representation which is not only tailored for the task of interest but also close to
the target-domain representation. Therefore, the source-domain task of
interest solution (e.g. a classifier for classification tasks) which is jointly trained with the source-domain representation can be applicable to
both the source and target representations. Using the MNIST, FashionMNIST, NIST, EMNIST, and SUN RGB-D datasets, we show that ZDDA can perform domain adaptation in classification tasks without access
to task-relevant target-domain training data. We also extend ZDDA to
perform sensor fusion in the SUN RGB-D scene classification task by simulating task-relevant target-domain representations with task-relevant
source-domain data. To the best of our knowledge, ZDDA is the first
domain adaptation and sensor fusion method which requires no taskrelevant target-domain data. The underlying principle is not particular
to computer vision data, but should be extensible to other domains