Discriminative Middle-Level Parts Mining for Object Detection

Dong LI  Yali LI  Shengjin WANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E98-D   No.11   pp.1950-1957
Publication Date: 2015/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDP7200
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
object detection,  discriminative part mining,  unsupervised part training,  part selection,  

Full Text: PDF(1.8MB)>>
Buy this Article

Middle-level parts have attracted great attention in the computer vision community, acting as discriminative elements for objects. In this paper we propose an unsupervised approach to mine discriminative parts for object detection. This work features three aspects. First, we introduce an unsupervised, exemplar-based training process for part detection. We generate initial parts by selective search and then train part detectors by exemplar SVM. Second, a part selection model based on consistency and distinctiveness is constructed to select effective parts from the candidate pool. Third, we combine discriminative part mining with the deformable part model (DPM) for object detection. The proposed method is evaluated on the PASCAL VOC2007 and VOC2010 datasets. The experimental results demons-trate the effectiveness of our method for object detection.