Is object localization for free? – Weakly-supervised learning with convolutional neural networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

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

Résumé

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.
Fichier principal
Vignette du fichier
Oquab15.pdf (1.74 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01015140 , version 1 (25-06-2014)
hal-01015140 , version 2 (17-05-2015)

Identifiants

  • HAL Id : hal-01015140 , version 2

Citer

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⟩
2842 Consultations
9136 Téléchargements

Partager

Gmail Facebook X LinkedIn More