Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning

June 2012

Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning

Authors:

Jun-Yan Zhu, Jiajun Wu, Yan Xu, Eric Chang, and Zhuowen Tu
Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

Abstract:

Discovering object classes from images in a fully unsupervised way is an intrinsically ambiguous task; saliency detection approaches however ease the burden on unsupervised learning. We develop an algorithm for simultaneously localizing objects and discovering object classes via bottom-up (saliency-guided) multiple class learning (bMCL), and make the following contributions: (1) saliency detection is adopted to convert unsupervised learning into multiple instance learning, formulated as bottom-up multiple class learning (bMCL); (2) we utilize the Discriminative EM (DiscEM) to solve our bMCL problem and show DiscEM's connection to the MIL-Boost method[34]; (3) localizing objects, discovering object classes, and training object detectors are performed simultaneously in an integrated framework; (4) significant improvements over the existing methods for multi-class object discovery are observed. In addition, we show single class localization as a special case in our bMCL framework and we also demonstrate the advantage of bMCL over purely data-driven saliency methods.
@conference{Zhu-2012-125703,
author = {Jun-Yan Zhu And Jiajun Wu And Yan Xu And Eric Chang And Zhuowen Tu},
title = {Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2012},
month = {June},
pages = {3218 - 3225},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.