%0 Conference Proceedings
%T Multi-task Bilinear Classifiers for Visual Domain Adaptation
%A Jiaolong Xu
%A Sebastian Ramos
%A Xu Hu
%A David Vazquez
%A Antonio Lopez
%B Advances in Neural Information Processing Systems Workshop
%D 2013
%F Jiaolong Xu2013
%O ADAS; 600.054; 600.057; 601.217;ISE
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2340), last updated on Thu, 10 Nov 2016 12:24:02 +0100
%X We propose a method that aims to lessen the significant accuracy degradationthat a discriminative classifier can suffer when it is trained in a specific domain (source domain) and applied in a different one (target domain). The principal reason for this degradation is the discrepancies in the distribution of the features that feed the classifier in different domains. Therefore, we propose a domain adaptation method that maps the features from the different domains into a common subspace and learns a discriminative domain-invariant classifier within it. Our algorithm combines bilinear classifiers and multi-task learning for domain adaptation.The bilinear classifier encodes the feature transformation and classificationparameters by a matrix decomposition. In this way, specific feature transformations for multiple domains and a shared classifier are jointly learned in a multi-task learning framework. Focusing on domain adaptation for visual object detection, we apply this method to the state-of-the-art deformable part-based model for cross domain pedestrian detection. Experimental results show that our method significantly avoids the domain drift and improves the accuracy when compared to several baselines.
%K Domain Adaptation
%K Pedestrian Detection
%K ADAS
%U http://refbase.cvc.uab.es/files/xrh2013.pdf