Domain adaptation algorithms aim at handling the shift between source and target domains. A classifier is trained on images from the source domain; and the classifier recognizes objects in images from the target domain. In this paper, we present a joint subspace and dictionary learning framework for domain adaptation. Our approach simultaneously exploits the low-dimensional structures in two do- mains and the sparsity of features in the projected subspace. Specifically, we first learn domain-specific subspaces from the source and target domains respectively that can decrease the mismatch between source and target domains. Then we project features from each domain onto their domain- specific subspaces. From the projected features, a common domain-invariant dictionary for both domains is learned. Our approach handles domain shift caused by different classes of features; e.g., SURF and SIFT. In addition, the features can have different dimensions. Our framework applies to both cross-domain adaptation (cross-DA) and multiple source domain adaptation (multi-DA). Our experimental results on the benchmark dataset show that our algorithm outperforms the state of the art.
Conference Dates: December 7, 2013
Conference Location: Sydney, -1
Conference Title: The 1st International Workshop on Visual Domain Adaptation and Dataset Bias
Pub Type: Conferences