Name
Title | ||
|---|---|---|
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation |
Abstract | ||
|---|---|---|
From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of highly discriminative intermediate features that we call Part-based One-vs.-One Features (POOFs). Each of these features specializes in discrimination between two particular classes based on the appearance at a particular part. We demonstrate the particular usefulness of these features for fine-grained visual categorization with new state-of-the-art results on bird species identification using the Caltech UCSD Birds (CUB) dataset and parity with the best existing results in face verification on the Labeled Faces in the Wild (LFW) dataset. Finally, we demonstrate the particular advantage of POOFs when training data is scarce. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CVPR.2013.128 | CVPR |
Keywords | Field | DocType |
face recognition,feature extraction,CUB dataset,Caltech UCSD birds,LFW dataset,POOF,attribute estimation,face verification,fine grained visual categorization,labeled faces in the wild,part-based one-vs.-one features,attributes,face verification,fine-grained visual categorization,part-based recognition | Face verification,Computer science,Species identification,Artificial intelligence,Discriminative model,Training set,Computer vision,Facial recognition system,Categorization,Pattern recognition,Speech recognition,Feature extraction,Face recognition feature extraction | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
127 | 7.30 | 28 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Thomas Berg | 1 | 207 | 12.42 |
| Peter N. Belhumeur | 2 | 12242 | 1001.27 |