Name
Abstract | ||
|---|---|---|
We address the problem of identifying specific instances of a class (cars) from a set of images all belonging to that class. Although we cannot build a model for any particular instance (as we may be provided with only one "training" example of it), we can use information extracted from observ- ing other members of the class. We pose this task as a learning problem, in which the learner is given image pairs, labeled as matching or not, and must discover which image features are most consistent for matching in- stances and discriminative for mismatches. We explore a patch based representation, where we model the distributions of similarity measure- ments defined on the patches. Finally, we describe an algorithm that selects the most salient patches based on a mutual information criterion. This algorithm performs identification well for our challenging dataset of car images, after matching only a few, well chosen patches. |
Year | Venue | Keywords |
|---|---|---|
2004 | NIPS | information extraction,mutual information,image features |
Field | DocType | Citations |
Pattern recognition,Feature (computer vision),Computer science,Visual identification,Mutual information,Artificial intelligence,Discriminative model,Machine learning,Salient | Conference | 13 |
PageRank | References | Authors |
1.68 | 9 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Andras Ferencz | 1 | 181 | 14.77 |
| Erik G. Miller | 2 | 1861 | 126.56 |
| Jitendra Malik | 3 | 39445 | 3782.10 |