Multi-fold MIL Training for Weakly Supervised Object Localization

Ramazan Gokberk Cinbis 1 Jakob Verbeek 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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 high-dimensional representations, such as the Fisher vectors, are used. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset. Compared to state-of-the-art weakly supervised detectors, our approach better localizes objects in the training images, which translates into improved detection performance.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2014, Columbus, United States. IEEE, pp.2409-2416, 2014, 〈10.1109/CVPR.2014.309〉
Liste complète des métadonnées

Littérature citée [31 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00975746
Contributeur : Thoth Team <>
Soumis le : mercredi 9 avril 2014 - 09:45:24
Dernière modification le : mercredi 11 avril 2018 - 01:58:54
Document(s) archivé(s) le : mercredi 9 juillet 2014 - 11:25:55

Fichiers

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

Identifiants

Collections

Citation

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid. Multi-fold MIL Training for Weakly Supervised Object Localization. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2014, Columbus, United States. IEEE, pp.2409-2416, 2014, 〈10.1109/CVPR.2014.309〉. 〈hal-00975746〉

Partager

Métriques

Consultations de la notice

1332

Téléchargements de fichiers

5264