TY  - CONF
AU  - Jiaolong Xu
AU  - David Vazquez
AU  - Krystian Mikolajczyk
AU  - Antonio Lopez
A2  - ICRA
PY  - 2016//
TI  - Hierarchical online domain adaptation of deformable part-based models
BT  - IEEE International Conference on Robotics and Automation
SP  - 5536
EP  - 5541
KW  - Domain Adaptation
KW  - Pedestrian Detection
N2  - We propose an online domain adaptation method for the deformable part-based model (DPM). The online domain adaptation is based on a two-level hierarchical adaptation tree, which consists of instance detectors in the leaf nodes and a category detector at the root node. Moreover, combined with a multiple object tracking procedure (MOT), our proposal neither requires target-domain annotated data nor revisiting the source-domain data for performing the source-to-target domain adaptation of the DPM. From a practical point of view this means that, given a source-domain DPM and new video for training on a new domain without object annotations, our procedure outputs a new DPM adapted to the domain represented by the video. As proof-of-concept we apply our proposal to the challenging task of pedestrian detection. In this case, each instance detector is an exemplar classifier trained online with only one pedestrian per frame. The pedestrian instances are collected by MOT and the hierarchical model is constructed dynamically according to the pedestrian trajectories. Our experimental results show that the adapted detector achieves the accuracy of recent supervised domain adaptation methods (i.e., requiring manually annotated targetdomain data), and improves the source detector more than 10 percentage points.
UR  - https://ieeexplore.ieee.org/document/7487769
L1  - http://refbase.cvc.uab.es/files/XVM2016.pdf
UR  - http://dx.doi.org/10.1109/ICRA.2016.7487769
N1  - ADAS; 600.085; 600.082; 600.076
ID  - Jiaolong Xu2016
ER  -