34. WEAKLY SUPERVISED OBJECT RECOGNITION AND LOCALIZATION WITH STABLE SEGMENTATIONS

Department: Computer Science & Engineering
Faculty Advisor(s): Serge Belongie

Primary Student
Name: Carolina Galleguillos
Email: cgallegu@ucsd.edu
Phone: 858-539-6008
Grad Year: 2010

Abstract
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learning object classifiers from weakly labeled image data, where only the presence of an object in an image is known, but not its location. Some recent work has explored the application of MIL algorithms to the tasks of image categorization and natural scene classification. In this paper we extend these ideas in a framework that uses MIL to recognize and localize objects in images. This task is challenging in real world scenes since objects may vary in scale, position, and viewpoint; in addition, they may be surrounded by background clutter, occluded by other objects, and obscured by poor image quality. To achieve object categorization, we employ state of the art image descriptors and multiple stable segmentations. These components, combined with a powerful MIL algorithm, form our object recognition system called MILSS. We show highly competitive object categorization results on the Caltech dataset. To evaluate the performance of our algorithm further, we introduce the challenging Landmarks-18 dataset, a collection of photographs of famous landmarks from around the world. The results on this new dataset show the great potential of our proposed algorithm.

Related Links:

1. graphics.ucsd.edu/~carolina

« Back to Posters or Search Results