Skip navigation.

UCSD Computer Vision

Weakly Supervised Object Recognition and Localization

Carolina Galleguillos, Boris Babenko, Andrew Rabinovich, Serge Belongie


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. To achieve this 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 Publications

Babenko B., Varma N., Dollar P., Belongie S., "Multiple Instance Learning with Manifold Bags", International Conference on Machine Learning (ICML), Bellevue, WA, 2011. [BibTex][pdf]
Galleguillos C., Babenko B., Rabinovich A., Belongie S., "Weakly Supervised Object Recognition and Localization with Stable Segmentations", European Conference on Computer Vision (ECCV), Marseille, France, 2008. [BibTex][pdf]
Rabinovich A., Lange T., Buhmann J., Belongie S., "Model Order Selection and Cue Combination for Image Segmentation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New York City, 2006. [BibTex][pdf]