Large-scale knowledge transfer for object localization in ImageNet

11 years 6 months ago
Large-scale knowledge transfer for object localization in ImageNet
ImageNet is a large-scale database of object classes with millions of images. Unfortunately only a small fraction of them is manually annotated with bounding-boxes. This prevents useful developments, such as learning reliable object detectors for thousands of classes. In this paper we propose to automatically populate ImageNet with many more bounding-boxes, by leveraging existing manual annotations. The key idea is to localize objects of a target class for which annotations are not available, by transferring knowledge from related source classes with available annotations. We distinguish two kinds of source classes: ancestors and siblings. Each source provides knowledge about the plausible location, appearance and context of the target objects, which induces a probability distribution over windows in images of the target class. We learn to combine these distributions so as to maximize the location accuracy of the most probable window. Finally, we employ the combined distribution in a ...
Matthieu Guillaumin, Vittorio Ferrari
Added 28 Sep 2012
Updated 28 Sep 2012
Type Journal
Year 2012
Where CVPR
Authors Matthieu Guillaumin, Vittorio Ferrari
Comments (0)