Low-Rank Subspace Override for Unsupervised Domain Adaptation
This addresses the challenge of poor generalization across domains in applications like robotics and visual classification, offering a fast and stable solution.
The paper tackles the problem of domain adaptation by proposing a method that uses a single data snapshot to find a domain-invariant subspace in closed form, achieving remarkable performance across text and image classification tasks.
Current supervised learning models cannot generalize well across domain boundaries, which is a known problem in many applications, such as robotics or visual classification. Domain adaptation methods are used to improve these generalization properties. However, these techniques suffer either from being restricted to a particular task, such as visual adaptation, require a lot of computational time and data, which is not always guaranteed, have complex parameterization, or expensive optimization procedures. In this work, we present an approach that requires only a well-chosen snapshot of data to find a single domain invariant subspace. The subspace is calculated in closed form and overrides domain structures, which makes it fast and stable in parameterization. By employing low-rank techniques, we emphasize on descriptive characteristics of data. The presented idea is evaluated on various domain adaptation tasks such as text and image classification against state of the art domain adaptation approaches and achieves remarkable performance across all tasks.