Joint hierarchical learning for efficient multi-class object detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Joint hierarchical learning for efficient multi-class object detection

Résumé

In addition to multi-class classification, the multi-class object detection task consists further in classifying a dominating background label. In this work, we present a novel approach where relevant classes are ranked higher and background labels are rejected. To this end, we arrange the classes into a tree structure where the classifiers are trained in a joint framework combining ranking and classification constraints. Our convex problem formulation naturally allows to apply a tree traversal algorithm that searches for the best class label and progressively rejects background labels. We evaluate our approach on the PASCAL VOC 2007 dataset and show a considerable speed-up of the detection time with increased detection performance.
Fichier non déposé

Dates et versions

hal-01296239 , version 1 (31-03-2016)

Identifiants

  • HAL Id : hal-01296239 , version 1

Citer

Hamidreza Odabai Fard, Mohamed Chaouch, Quoc-Cuong Pham, Antoine Vacavant, Thierry Chateau. Joint hierarchical learning for efficient multi-class object detection. Applications of Computer Vision (WACV), 2014 IEEE Winter Conference on, Mar 2014, Steamboat Springs, United States. pp.261--268. ⟨hal-01296239⟩
97 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More