Deformable Part-Based Model Transfer for Object Detection

Zhiwei RUAN  Guijin WANG  Xinggang LIN  Jing-Hao XUE  Yong JIANG  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E97-D   No.5   pp.1394-1397
Publication Date: 2014/05/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E97.D.1394
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
Keyword: 
deformable part model,  object detection,  transfer learning,  

Full Text: PDF>>
Buy this Article




Summary: 
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.