Sciweavers

Share
CVPR
2006
IEEE

Unsupervised Learning of Categories from Sets of Partially Matching Image Features

9 years 11 months ago
Unsupervised Learning of Categories from Sets of Partially Matching Image Features
We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into a space where they cluster according to their partial-match feature correspondences. After efficiently computing the pairwise affinities between the input images in this space, a spectral clustering technique is used to recover the primary groupings among the images. We introduce an efficient means of refining these groupings according to intra-cluster statistics over the subsets of features selected by the partial matches between the images, and based on an optional, variable amount of user supervision. We compute the consistent subsets of feature correspondences within a grouping to infer category feature masks. The output of the algorithm is a partition of the data into a set of learned categories, and a set of classifiers trained from these ranked partitions that can recognize the categories in novel ima...
Kristen Grauman, Trevor Darrell
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2006
Where CVPR
Authors Kristen Grauman, Trevor Darrell
Comments (0)
books