Adapted Domain Specific Class Means

Gabriela Csurka, Boris Chidlovskii, Stephane Clinchant; Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops, 2015, pp. 7-11

We address the problem of domain adaptation (DA) from one or multiple source domains to a target domain. Most of the existing DA methods assume that source data is largely available. Such an assumption rarely holds in real applications, for both technical and legal reasons. More realistic are situations where source domain observations become quickly unavailable, but only some domain representatives can be retained, either as source instances or as their aggregation. In this paper therefore we focus on the Domain Specific Class Means (DSCM) classifier that can handle such scenario and we combine it with Stacked Marginalized Denoising Autoencoders. We propose a method that exploits the correlation between the target data and source prototypes without the need of target labels and automatically adapts these class means to the target dataset. We show, on a variety of datasets and tasks, that the method can be applied successfully even when no labeled target is available and also that it can provide performance comparable to the case where dense knowledge (all source data) is available.