Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning

Abstract : Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when using high-dimensional representations, such as Fisher vectors and convolutional neural network features. We also propose a window refinement method, which improves the localization accuracy by incorporating an objectness prior. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset, which verifies the effectiveness of our approach.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2017, 39 (1), pp.189-203
Liste complète des métadonnées

https://hal.inria.fr/hal-01123482
Contributeur : Thoth Team <>
Soumis le : lundi 22 février 2016 - 16:32:28
Dernière modification le : mardi 3 janvier 2017 - 14:38:58
Document(s) archivé(s) le : lundi 23 mai 2016 - 14:33:41

Fichier

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

Identifiants

  • HAL Id : hal-01123482, version 3
  • ARXIV : 1503.00949

Collections

Citation

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2017, 39 (1), pp.189-203. <hal-01123482v3>

Partager

Métriques

Consultations de
la notice

735

Téléchargements du document

819