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.
Keywords
Discriminative modelCategorizationComputer scienceArtificial intelligenceFace (sociological concept)Pattern recognition (psychology)Set (abstract data type)Class (philosophy)Domain (mathematical analysis)Identification (biology)Machine learningMathematics
Affiliated Institutions
Related Publications
Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction
Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized,...
CosFace: Large Margin Cosine Loss for Deep Face Recognition
Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face veri...
Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification
We propose a method of face verification that takes advantage of a reference set of faces, disjoint by identity from the test faces, labeled with identity and face part location...
Probabilistic Elastic Matching for Pose Variant Face Verification
Pose variation remains to be a major challenge for real-world face recognition. We approach this problem through a probabilistic elastic matching method. We take a part based re...
Fisher Vector Faces in the Wild
Several recent papers on automatic face verification have significantly raised the performance bar by developing novel, specialised representations that outperform standard feat...
Publication Info
- Year
- 2013
- Type
- article
- Citations
- 378
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
378
OpenAlex
Cite This
Thomas Berg,
Peter N. Belhumeur
(2013).
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation.
.
https://doi.org/10.1109/cvpr.2013.128
Identifiers
- DOI
- 10.1109/cvpr.2013.128