Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks

Maxime Oquab 1, 2, 3 Léon Bottou 4 Ivan Laptev 2, 3 Josef Sivic 2, 3
2 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : Convolutional neural networks (CNN) have recently shown outstanding image classification performance in the large-scale visual recognition challenge (ILSVRC2012). The success of CNNs is attributed to their ability to learn rich mid-level image representations as opposed to hand-designed low-level features used in other image classification methods. Learning CNNs, however, amounts to estimating millions of parameters and requires a very large number of annotated image samples. This property currently prevents application of CNNs to problems with limited training data. In this work we show how image representations learned with CNNs on large-scale annotated datasets can be efficiently transferred to other visual recognition tasks with limited amount of training data. We design a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset. We show that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification, outperforming the current state of the art on Pascal VOC 2007 and 2012 datasets. We also show promising results for object and action localization.
Type de document :
Communication dans un congrès
IEEE Conference on Computer Vision and Pattern Recognition, Jun 2014, Columbus, OH, United States. 2013
Liste complète des métadonnées

Littérature citée [50 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00911179
Contributeur : Josef Sivic <>
Soumis le : samedi 13 septembre 2014 - 12:39:59
Dernière modification le : vendredi 25 mai 2018 - 12:02:06
Document(s) archivé(s) le : dimanche 14 décembre 2014 - 10:21:31

Fichier

oquab14.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00911179, version 2

Collections

Citation

Maxime Oquab, Léon Bottou, Ivan Laptev, Josef Sivic. Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2014, Columbus, OH, United States. 2013. 〈hal-00911179v2〉

Partager

Métriques

Consultations de la notice

2445

Téléchargements de fichiers

962