Simultaneous Learning and Alignment: Multi-Instance and Multi-Pose Learning

Abstract : In object recognition in general and in face detection in particular, data alignment is necessary to achieve good classification results with certain statistical learning approaches such as Viola-Jones. Data can be aligned in one of two ways: (1) by separating the data into coherent groups and training separate classifiers for each; (2) by adjusting training samples so they lie in correspondence. If done manually, both procedures are labor intensive and can significantly add to the cost of labeling. In this paper we present a unified boosting framework for simultaneous learning and alignment. We present a novel boosting algorithm for Multiple Pose Learning (mpl), where the goal is to simultaneously split data into groups and train classifiers for each. We also review Multiple Instance Learning (mil), and in particular mil-boost, and describe how to use it to simultaneously train a classifier and bring data into correspondence. We show results on variations of LFW and MNIST, demonstrating the potential of these approaches.
Type de document :
Communication dans un congrès
Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00326736
Contributeur : Peter Sturm <>
Soumis le : dimanche 5 octobre 2008 - 13:20:08
Dernière modification le : lundi 6 octobre 2008 - 09:34:25
Document(s) archivé(s) le : jeudi 3 juin 2010 - 22:19:50

Fichier

BabenkoEtAlECCV08simul.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00326736, version 1

Collections

Citation

Boris Babenko, Piotr Dollár, Zhuowen Tu, Serge Belongie. Simultaneous Learning and Alignment: Multi-Instance and Multi-Pose Learning. Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition, Oct 2008, Marseille, France. 2008. 〈inria-00326736〉

Partager

Métriques

Consultations de la notice

628

Téléchargements de fichiers

364