SPLeaP: Soft Pooling of Learned Parts for Image Classification

Abstract : The aggregation of image statistics – the so-called pooling step of image classification algorithms – as well as the construction of part-based models, are two distinct and well-studied topics in the literature. The former aims at leveraging a whole set of local descriptors that an image can contain (through spatial pyramids or Fisher vectors for instance) while the latter argues that only a few of the regions an image contains are actually useful for its classification. This paper bridges the two worlds by proposing a new pooling framework based on the discovery of useful parts involved in the pooling of local representations. The key contribution lies in a model integrating a boosted non-linear part clas-sifier as well as a parametric soft-max pooling component, both trained jointly with the image classifier. The experimental validation shows that the proposed model not only consistently surpasses standard pooling approaches but also improves over state-of-the-art part-based models, on several different and challenging classification tasks.
Type de document :
Communication dans un congrès
4th European Conference on Computer Vision (ECCV 2016), Oct 2016, Amsterdam, Netherlands. 2016
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01350562
Contributeur : Frederic Jurie <>
Soumis le : mardi 2 août 2016 - 15:11:05
Dernière modification le : jeudi 4 août 2016 - 01:03:22
Document(s) archivé(s) le : jeudi 3 novembre 2016 - 12:38:06

Fichier

1646.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01350562, version 1

Collections

Citation

Praveen Kulkarni, Frédéric Jurie, Joaquin Zepeda, Patrick Pérez, Louis Chevallier. SPLeaP: Soft Pooling of Learned Parts for Image Classification. 4th European Conference on Computer Vision (ECCV 2016), Oct 2016, Amsterdam, Netherlands. 2016. <hal-01350562>

Partager

Métriques

Consultations de
la notice

502

Téléchargements du document

343