For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Deformable Part-Based Model Transfer for Object Detection
Zhiwei RUAN Guijin WANG Xinggang LIN Jing-Hao XUE Yong JIANG
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/05/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
deformable part model, object detection, transfer learning,
Full Text: PDF(849.1KB)>>
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.