Learning the Roots of Visual Domain Shift
This work addresses domain adaptation for computer vision by identifying specific image regions causing shift, offering an incremental improvement over existing methods.
The paper tackles the problem of localizing the spatial origins of visual domain shift in images by learning domainness maps, and shows that using these maps as a preprocessing step strongly improves classification performance, achieving state-of-the-art results on the Office dataset.
In this paper we focus on the spatial nature of visual domain shift, attempting to learn where domain adaptation originates in each given image of the source and target set. We borrow concepts and techniques from the CNN visualization literature, and learn domainnes maps able to localize the degree of domain specificity in images. We derive from these maps features related to different domainnes levels, and we show that by considering them as a preprocessing step for a domain adaptation algorithm, the final classification performance is strongly improved. Combined with the whole image representation, these features provide state of the art results on the Office dataset.