Tree-structured CRF Models for Interactive Image Labeling

Thomas Mensink 1, 2, * Jakob Verbeek 1 Gabriela Csurka 2
* Auteur correspondant
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We propose structured prediction models for image labeling that explicitly take into account dependencies among image labels. In our tree structured models, image labels are nodes, and edges encode dependency relations. To allow for more complex dependencies, we combine labels in a single node, and use mixtures of trees. Our models are more expressive than independent predictors, and lead to more accurate label predictions. The gain becomes more significant in an interactive scenario where a user provides the value of some of the image labels at test time. Such an interactive scenario offers an interesting trade-off between label accuracy and manual labeling effort. The structured models are used to decide which labels should be set by the user, and transfer the user input to more accurate predictions on other image labels. We also apply our models to attribute-based image classification, where attribute predictions of a test image are mapped to class probabilities by means of a given attribute-class mapping. Experimental results on three publicly available benchmark data sets show that in all scenarios our structured models lead to more accurate predictions, and leverage user input much more effectively than state-of-the-art independent models.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2013, 35 (2), pp.476-489. 〈10.1109/TPAMI.2012.100〉
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00688143
Contributeur : Thoth Team <>
Soumis le : lundi 16 avril 2012 - 18:29:19
Dernière modification le : mercredi 11 avril 2018 - 01:59:35
Document(s) archivé(s) le : lundi 26 novembre 2012 - 14:50:23

Fichiers

MVC2012pami.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Thomas Mensink, Jakob Verbeek, Gabriela Csurka. Tree-structured CRF Models for Interactive Image Labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2013, 35 (2), pp.476-489. 〈10.1109/TPAMI.2012.100〉. 〈hal-00688143〉

Partager

Métriques

Consultations de la notice

704

Téléchargements de fichiers

909