Abstract

Domain adaptation is an important emerging topic in com- puter vision. In this paper, we present one of the first studies of domain shift in the context of ob ject recognition. We introduce a method that adapts ob ject models acquired in a particular visual domain to new imag- ing conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution. The transformation is learned in a supervised manner and can be applied to categories for which there are no labeled examples in the new domain. While we focus our evaluation on ob ject recognition tasks, the transform-based adapta- tion technique we develop is general and could be applied to non-image data. Another contribution is a new multi-domain ob ject database, freely available for download. We experimentally demonstrate the ability of our method to improve recognition on categories with few or no target do- main labels and moderate to large changes in the imaging conditions.