Currently, the state-of-the-art image classification algorithms outperform the best available object detector by a big margin in terms of average precision. We, therefore, propose a simple yet principled approach that allows us to leverage object detection through image classification on supporting regions specified by a preliminary object detector. Using a simple bag-of- words model based image classification algorithm, we leveraged the performance of the deformable model objector from 35.9% to 39.5% in average precision over 20 categories on standard PASCAL VOC 2007 detection dataset.
@article{arxiv.1604.01841,
title = {A Classification Leveraged Object Detector},
author = {Miao Sun and Tony X. Han and Zhihai He},
journal= {arXiv preprint arXiv:1604.01841},
year = {2016}
}
Comments
Work in 2013, which contained some detailed algorithms for PASCAL VOC 2012 detection competition