POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation

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 discrimina...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 955 - 962
Main Authors Berg, Thomas, Belhumeur, Peter N.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
Accuracy
attributes
Birds
Face
face verification
Feature extraction
fine-grained visual categorization
Histograms
Image color analysis
part-based recognition
Training
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.128