Is object localization for free? – Weakly-supervised learning with convolutional neural networks

Maxime Oquab 1, 2, 3 Léon Bottou 4 Ivan Laptev 2, 3 Josef Sivic 2, 3
3 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Successful methods for visual object recognition typically rely on training datasets containing lots of richly annotated images. Detailed image annotation, e.g. by object bounding boxes, however, is both expensive and often subjective. We describe a weakly supervised convolutional neural network (CNN) for object classification that relies only on image-level labels, yet can learn from cluttered scenes containing multiple objects. We quantify its object classification and object location prediction performance on the Pascal VOC 2012 (20 object classes) and the much larger Microsoft COCO (80 object classes) datasets. We find that the network (i) outputs accurate image-level labels, (ii) predicts approximate locations (but not extents) of objects, and (iii) performs comparably to its fully-supervised counterparts using object bounding box annotation for training.
Type de document :
Communication dans un congrès
IEEE Conference on Computer Vision and Pattern Recognition, Jun 2015, Boston, United States
Liste complète des métadonnées

Littérature citée [61 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01015140
Contributeur : Josef Sivic <>
Soumis le : dimanche 17 mai 2015 - 21:56:24
Dernière modification le : jeudi 11 janvier 2018 - 06:23:05
Document(s) archivé(s) le : mardi 15 septembre 2015 - 01:12:43

Fichier

Oquab15.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01015140, version 2

Collections

Citation

Maxime Oquab, Léon Bottou, Ivan Laptev, Josef Sivic. Is object localization for free? – Weakly-supervised learning with convolutional neural networks. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2015, Boston, United States. 〈hal-01015140v2〉

Partager

Métriques

Consultations de la notice

2064

Téléchargements de fichiers

3607