Saliency-Guided Unsupervised Object Class Discovery

Abstract

In this paper, we tackle the problem of common object (multiple classes) discovery from a set of input images, where we assume the presence of one object class in each image. This problem is, loosely speaking, unsupervised since we do not know a priori about the object type, location, and scale in each image. We observe that the general task of object class discovery in a fully unsupervised manner is intrinsically ambiguous; here we adopt saliency detection to propose candidate image windows/patches to turn an unsupervised learning problem into a weakly-supervised learning problem. In the paper, we propose an algorithm for simultaneously localizing objects and discovering object classes via bottom-up (saliency-guided) multiple class learning (bMCL). Our contributions are three-fold: (1) we adopt saliency detection to convert unsupervised learning into multiple instance learning, formulated as bottom-up multiple class learning (bMCL); (2) we propose an integrated framework that simultaneously performs object localization, object class discovery, and object detector training; (3) we demonstrate that our framework yields significant improvements over existing methods for multi-class object discovery and possess evident advantages over competing methods in computer vision. In addition, although saliency detection has recently attracted much attention, its practical usage for high-level vision tasks has yet to be justified. Our method validates the usefulness of saliency detection to output “noisy input” for a top-down method to extract common patterns.

paper thumbnail

Paper

CVPR 2012 paper, 4.7MB
TPAMI 2014 paper, 18.7MB

Citation

Jun-Yan Zhu, Jiajun Wu, Yichen Wei, Eric Chang, and Zhuowen Tu. "Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning", in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. Bibtex

Jun-Yan Zhu, Jiajun Wu, Yan Xu, Eric Chang, and Zhuowen Tu. "Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning", in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2015. Bibtex


Additional Materials

Dataset

The datasets we used include: SIVAL, iCoseg, and 3D Object Category.


Acknowledgement

We thank Jiayan Jiang, Tao Chen, Patrick Gallagher, and Piotr Dollar for encouraging discussions

Related Papers

Xinggang Wang, Zhengdong Zhang, Yi Ma, Xiang Bai, Wenyu Liu, and Zhuowen Tu. "Robust Subspace Discovery via Relaxed Rank Minimization", in Neural Computation, 2014.

Quannan Li, Jiajun Wu, and Zhuowen Tu. "Harvesting Mid-level Visual Concepts from Large-scale Internet Images", in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.


Funding

This research is supported in part by: