Learning Equivariant Structured Output SVM Regressors

Abstract : Equivariance and invariance are often desired properties of a computer vision system. However, currently available strategies generally rely on virtual sampling, leaving open the question of how many samples are necessary, on the use of invariant feature representations, which can mistakenly discard information relevant to the vision task, or on the use of latent variable models, which result in non-convex training and expensive inference at test time. We propose here a generalization of structured output SVM regressors that can incorporate equivariance and invariance into a convex training procedure, enabling the incorporation of large families of transformations, while maintaining optimality and tractability. Importantly, test time inference does not require the estimation of latent variables, resulting in highly efficient objective functions. This results in a natural formulation for treating equivariance and invariance that is easily implemented as an adaptation of off-the-shelf optimization software, obviating the need for ad hoc sampling strategies. Theoretical results relating to vicinal risk, and experiments on challenging aerial car and pedestrian detection tasks show the effectiveness of the proposed solution.
Type de document :
Communication dans un congrès
International Conference on Computer Vision, Nov 2011, Barcelona, Spain. pp.959-966, 2011, 2011 IEEE International Conference on Computer Vision (ICCV). 〈10.1109/ICCV.2011.6126339〉
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00855739
Contributeur : Matthew Blaschko <>
Soumis le : vendredi 31 janvier 2014 - 16:40:00
Dernière modification le : vendredi 6 avril 2018 - 13:32:01
Document(s) archivé(s) le : jeudi 6 avril 2017 - 10:40:49

Fichier

vedaldi11a.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Andrea Vedaldi, Matthew Blaschko, Andrew Zisserman. Learning Equivariant Structured Output SVM Regressors. International Conference on Computer Vision, Nov 2011, Barcelona, Spain. pp.959-966, 2011, 2011 IEEE International Conference on Computer Vision (ICCV). 〈10.1109/ICCV.2011.6126339〉. 〈hal-00855739〉

Partager

Métriques

Consultations de la notice

292

Téléchargements de fichiers

186