The transfer of prior knowledge from source domains can improve the performance of learning when the training data in a target domain are insufficient. In this paper we propose a new strategy to transfer deformable part models (DPMs) for object detection, using offline-trained auxiliary DPMs of similar categories as source models to improve the performance of the target object detector. A DPM presents an object by using a root filter and several part filters. We use these filters of the auxiliary DPMs as prior knowledge and adapt the filters to the target object. With a latent transfer learning method, appropriate local features are extracted for the transfer of part filters. Our experiments demonstrate that this strategy can lead to a detector superior to some state-of-the-art methods.
Zhiwei RUAN
Tsinghua University
Guijin WANG
Tsinghua University
Xinggang LIN
Tsinghua University
Jing-Hao XUE
University College London
Yong JIANG
Canon Information Technology (Beijing) Co., LTD
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Zhiwei RUAN, Guijin WANG, Xinggang LIN, Jing-Hao XUE, Yong JIANG, "Deformable Part-Based Model Transfer for Object Detection" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 5, pp. 1394-1397, May 2014, doi: 10.1587/transinf.E97.D.1394.
Abstract: The transfer of prior knowledge from source domains can improve the performance of learning when the training data in a target domain are insufficient. In this paper we propose a new strategy to transfer deformable part models (DPMs) for object detection, using offline-trained auxiliary DPMs of similar categories as source models to improve the performance of the target object detector. A DPM presents an object by using a root filter and several part filters. We use these filters of the auxiliary DPMs as prior knowledge and adapt the filters to the target object. With a latent transfer learning method, appropriate local features are extracted for the transfer of part filters. Our experiments demonstrate that this strategy can lead to a detector superior to some state-of-the-art methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E97.D.1394/_p
Copy
@ARTICLE{e97-d_5_1394,
author={Zhiwei RUAN, Guijin WANG, Xinggang LIN, Jing-Hao XUE, Yong JIANG, },
journal={IEICE TRANSACTIONS on Information},
title={Deformable Part-Based Model Transfer for Object Detection},
year={2014},
volume={E97-D},
number={5},
pages={1394-1397},
abstract={The transfer of prior knowledge from source domains can improve the performance of learning when the training data in a target domain are insufficient. In this paper we propose a new strategy to transfer deformable part models (DPMs) for object detection, using offline-trained auxiliary DPMs of similar categories as source models to improve the performance of the target object detector. A DPM presents an object by using a root filter and several part filters. We use these filters of the auxiliary DPMs as prior knowledge and adapt the filters to the target object. With a latent transfer learning method, appropriate local features are extracted for the transfer of part filters. Our experiments demonstrate that this strategy can lead to a detector superior to some state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.E97.D.1394},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Deformable Part-Based Model Transfer for Object Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1394
EP - 1397
AU - Zhiwei RUAN
AU - Guijin WANG
AU - Xinggang LIN
AU - Jing-Hao XUE
AU - Yong JIANG
PY - 2014
DO - 10.1587/transinf.E97.D.1394
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2014
AB - The transfer of prior knowledge from source domains can improve the performance of learning when the training data in a target domain are insufficient. In this paper we propose a new strategy to transfer deformable part models (DPMs) for object detection, using offline-trained auxiliary DPMs of similar categories as source models to improve the performance of the target object detector. A DPM presents an object by using a root filter and several part filters. We use these filters of the auxiliary DPMs as prior knowledge and adapt the filters to the target object. With a latent transfer learning method, appropriate local features are extracted for the transfer of part filters. Our experiments demonstrate that this strategy can lead to a detector superior to some state-of-the-art methods.
ER -