WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks

Thibaut Durand 1 Nicolas Thome 1 Matthieu Cord 1
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : In this paper, we introduce a novel framework for WEakly supervised Learning of Deep cOnvolutional neu-ral Networks (WELDON). Our method is dedicated to automatically selecting relevant image regions from weak annotations , e.g. global image labels, and encompasses the following contributions. Firstly, WELDON leverages recent improvements on the Multiple Instance Learning paradigm, i.e. negative evidence scoring and top instance selection. Secondly, the deep CNN is trained to optimize Average Precision , and fine-tuned on the target dataset with efficient computations due to convolutional feature sharing. A thorough experimental validation shows that WELDON outper-forms state-of-the-art results on six different datasets.
Type de document :
Communication dans un congrès
29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Jun 2016, Las Vegas, NV, United States. 〈http://cvpr2016.thecvf.com/〉
Liste complète des métadonnées

Littérature citée [52 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01343785
Contributeur : Thibaut Durand <>
Soumis le : dimanche 10 juillet 2016 - 01:06:18
Dernière modification le : vendredi 23 novembre 2018 - 08:52:42

Fichier

weldon_cvpr2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01343785, version 1

Collections

Citation

Thibaut Durand, Nicolas Thome, Matthieu Cord. WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks. 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Jun 2016, Las Vegas, NV, United States. 〈http://cvpr2016.thecvf.com/〉. 〈hal-01343785〉

Partager

Métriques

Consultations de la notice

368

Téléchargements de fichiers

147