Persistence-based Pooling for Shape Pose Recognition

Abstract : In this paper, we propose a novel pooling approach for shape classification and recognition using the bag-of-words pipeline, based on topological persistence, a recent tool from Topological Data Analysis. Our technique extends the standard max-pooling, which summarizes the distribution of a visual feature with a single number, thereby losing any notion of spatiality. Instead, we propose to use topological persistence, and the derived persistence diagrams, to provide significantly more informative and spatially sensitive characterizations of the feature functions, which can lead to better recognition performance. Unfortunately, despite their conceptual appeal, persistence diagrams are difficult to handle , since they are not naturally represented as vectors in Euclidean space and even the standard metric, the bottleneck distance is not easy to compute. Furthermore, classical distances between diagrams, such as the bottleneck and Wasserstein distances, do not allow to build positive definite kernels that can be used for learning. To handle this issue, we provide a novel way to transform persistence diagrams into vectors, in which comparisons are trivial. Finally, we demonstrate the performance of our construction on the Non-Rigid 3D Human Models SHREC 2014 dataset, where we show that topological pooling can provide significant improvements over the standard pooling methods for the shape pose recognition within the bag-of-words pipeline.
Type de document :
Communication dans un congrès
6th International Workshop on Computational Topology in Image Context (CTIC 2016), Jun 2016, Marseille, France. 9667, CTIC 2016 Proceedings of the 6th International Workshop on Computational Topology in Image Context
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01301937
Contributeur : Thomas Bonis <>
Soumis le : lundi 24 octobre 2016 - 17:30:10
Dernière modification le : samedi 18 février 2017 - 01:14:01

Fichier

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

Identifiants

  • HAL Id : hal-01301937, version 2

Citation

Thomas Bonis, Maks Ovsjanikov, Steve Oudot, Frédéric Chazal. Persistence-based Pooling for Shape Pose Recognition. 6th International Workshop on Computational Topology in Image Context (CTIC 2016), Jun 2016, Marseille, France. 9667, CTIC 2016 Proceedings of the 6th International Workshop on Computational Topology in Image Context. <hal-01301937v2>

Partager

Métriques

Consultations de
la notice

342

Téléchargements du document

118