TY  - JOUR
AU  - Jiaolong Xu
AU  - Sebastian Ramos
AU  - David Vazquez
AU  - Antonio Lopez
PY  - 2014//
TI  - Domain Adaptation of Deformable Part-Based Models
T2  - TPAMI
JO  - IEEE Transactions on Pattern Analysis and Machine Intelligence
SP  - 2367
EP  - 2380
VL  - 36
IS  - 12
KW  - Domain Adaptation
KW  - Pedestrian Detection
N2  - The accuracy of object classifiers can significantly drop when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, adapting the classifiers to the scenario in which they must operate is of paramount importance. We present novel domain adaptation (DA) methods for object detection. As proof of concept, we focus on adapting the state-of-the-art deformable part-based model (DPM) for pedestrian detection. We introduce an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains. By taking into account the inherent structure in feature space (e.g., the parts in a DPM), we propose a structure-aware A-SSVM (SA-SSVM). Neither A-SSVM nor SA-SSVM needs to revisit the source-domain training data to perform the adaptation. Rather, a low number of target-domain training examples (e.g., pedestrians) are used. To address the scenario where there are no target-domain annotated samples, we propose a self-adaptive DPM based on a self-paced learning (SPL) strategy and a Gaussian Process Regression (GPR). Two types of adaptation tasks are assessed: from both synthetic pedestrians and general persons (PASCAL VOC) to pedestrians imaged from an on-board camera. Results show that our proposals avoid accuracy drops as high as 15 points when comparing adapted and non-adapted detectors.
SN  - 0162-8828
L1  - http://refbase.cvc.uab.es/files/XRV2014b.pdf
UR  - http://dx.doi.org/10.1109/TPAMI.2014.2327973
N1  - ADAS; 600.057; 600.054; 601.217; 600.076
ID  - Jiaolong Xu2014
ER  -