Deformable Part Models with CNN Features

Abstract : In this work we report on progress in integrating deep convo-lutional features with Deformable Part Models (DPMs). We substitute the Histogram-of-Gradient features of DPMs with Convolutional Neural Network (CNN) features, obtained from the top-most, fifth, convolutional layer of Krizhevsky's network [8]. We demonstrate that we thereby obtain a substantial boost in performance (+14.5 mAP) when compared to the baseline HOG-based models. This only partially bridges the gap between DPMs and the currently top-performing R-CNN method of [4], suggesting that more radical changes to DPMs may be needed.
Type de document :
Communication dans un congrès
European Conference on Computer Vision, Parts and Attributes Workshop, Sep 2014, Zurich, Switzerland. 〈https://computing.ece.vt.edu/~parikh/PnA2014/〉
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01109290
Contributeur : Stavros Tsogkas <>
Soumis le : lundi 26 janvier 2015 - 04:50:53
Dernière modification le : jeudi 7 février 2019 - 17:29:10
Document(s) archivé(s) le : lundi 27 avril 2015 - 10:11:09

Fichier

Savalle_cnndpm_PnA14.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01109290, version 1

Collections

Citation

Pierre-André Savalle, Stavros Tsogkas, George Papandreou, Iasonas Kokkinos. Deformable Part Models with CNN Features. European Conference on Computer Vision, Parts and Attributes Workshop, Sep 2014, Zurich, Switzerland. 〈https://computing.ece.vt.edu/~parikh/PnA2014/〉. 〈hal-01109290〉

Partager

Métriques

Consultations de la notice

766

Téléchargements de fichiers

679