@Article{JiaolongXu2016,
author="Jiaolong Xu
and Sebastian Ramos
and David Vazquez
and Antonio Lopez",
title="Hierarchical Adaptive Structural SVM for Domain Adaptation",
journal="International Journal of Computer Vision",
year="2016",
publisher="Springer US",
volume="119",
number="2",
pages="159--178",
optkeywords="Domain Adaptation",
optkeywords="Pedestrian Detection",
abstract="A key topic in classification is the accuracy loss produced when the data distribution in the training (source) domain differs from that in the testing (target) domain. This is being recognized as a very relevant problem for manycomputer vision tasks such as image classification, object detection, and object category recognition. In this paper, we present a novel domain adaptation method that leverages multiple target domains (or sub-domains) in a hierarchical adaptation tree. The core idea is to exploit the commonalities and differences of the jointly considered target domains. Given the relevance of structural SVM (SSVM) classifiers, we apply our idea to the adaptive SSVM (A-SSVM), which only requires the target domain samples together with the existing source-domain classifier for performing the desired adaptation. Altogether, we term our proposal as hierarchical A-SSVM (HA-SSVM).As proof of concept we use HA-SSVM for pedestrian detection, object category recognition and face recognition. In the former we apply HA-SSVM to the deformable partbased model (DPM) while in the rest HA-SSVM is applied to multi-category classifiers. We will show how HA-SSVM is effective in increasing the detection/recognition accuracy with respect to adaptation strategies that ignore the structure of the target data. Since, the sub-domains of the target data are not always known a priori, we shown how HA-SSVM can incorporate sub-domain discovery for object category recognition.",
optnote="ADAS; 600.085; 600.082; 600.076",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=2669), last updated on Sun, 19 Mar 2017 14:55:23 +0100",
issn="0920-5691",
doi="10.1007/s11263-016-0885-6",
file=":http://refbase.cvc.uab.es/files/XRV2016.pdf:PDF"
}