Co-localization in Real-World Images

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1464 - 1471
• Main Authors: Tang, Kevin, Joulin, Armand, Li-Jia Li, Li Fei-Fei
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Airplanes; Annotations; Co-localization; Computer vision; Conferences; Feature extraction; Joints; Localization; Noise; Noise measurement; Object Detection; Object recognition; Pascal (programming language); Pattern recognition; State of the art; Vectors; Volatile organic compounds
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2014.190

In this paper, we tackle the problem of co-localization in real-world images. Co-localization is the problem of simultaneously localizing (with bounding boxes) objects of the same class across a set of distinct images. Although similar problems such as co-segmentation and weakly supervised localization have been previously studied, we focus on being able to perform co-localization in real-world settings, which are typically characterized by large amounts of intra-class variation, inter-class diversity, and annotation noise. To address these issues, we present a joint image-box formulation for solving the co-localization problem, and show how it can be relaxed to a convex quadratic program which can be efficiently solved. We perform an extensive evaluation of our method compared to previous state-of-the-art approaches on the challenging PASCAL VOC 2007 and Object Discovery datasets. In addition, we also present a large-scale study of co-localization on ImageNet, involving ground-truth annotations for 3, 624 classes and approximately 1 million images.