End-to-End Kernel Learning with Supervised Convolutional Kernel Networks

Julien Mairal 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with supervision. We proceed by first proposing improvements of the recently-introduced convolutional kernel networks (CKNs) in the context of unsupervised learning; then, we derive backpropagation rules to take advantage of labeled training data. The resulting model is a new type of convolutional neural network, where optimizing the filters at each layer is equivalent to learning a linear subspace in a reproducing kernel Hilbert space (RKHS). We show that our method achieves reasonably competitive performance for image classification on some standard " deep learning " datasets such as CIFAR-10 and SVHN, and also for image super-resolution, demonstrating the applicability of our approach to a large variety of image-related tasks.
Type de document :
Communication dans un congrès
Advances in Neural Information Processing Systems (NIPS), Dec 2016, Barcelona, France
Liste complète des métadonnées


https://hal.inria.fr/hal-01387399
Contributeur : Julien Mairal <>
Soumis le : mardi 25 octobre 2016 - 15:04:13
Dernière modification le : lundi 7 novembre 2016 - 09:47:17

Fichier

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

Identifiants

  • HAL Id : hal-01387399, version 1

Collections

Citation

Julien Mairal. End-to-End Kernel Learning with Supervised Convolutional Kernel Networks. Advances in Neural Information Processing Systems (NIPS), Dec 2016, Barcelona, France. <hal-01387399>

Partager

Métriques

Consultations de
la notice

553

Téléchargements du document

460