Accéder directement au contenu Accéder directement à la navigation
Nouvelle interface
Communication dans un congrès

Crafting a multi-task CNN for viewpoint estimation

Abstract : Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the- art results for object category viewpoint estimation. However different ways of formulat- ing this problem have been proposed and the competing approaches have been explored with very different design choices. This paper presents a comparison of these approaches in a unified setting as well as a detailed analysis of the key factors that impact perfor- mance. Followingly, we present a new joint training method with the detection task and demonstrate its benefit. We also highlight the superiority of classification approaches over regression approaches, quantify the benefits of deeper architectures and extended training data, and demonstrate that synthetic data is beneficial even when using ImageNet training data. By combining all these elements, we demonstrate an improvement of ap- proximately 5% mAVP over previous state-of-the-art results on the Pascal3D+ dataset [28]. In particular for their most challenging 24 view classification task we improve the results from 31.1% to 36.1% mAVP.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [29 références]  Voir  Masquer  Télécharger
Contributeur : Renaud Marlet Connectez-vous pour contacter le contributeur
Soumis le : lundi 26 mars 2018 - 12:51:00
Dernière modification le : samedi 15 janvier 2022 - 03:56:30
Archivage à long terme le : : jeudi 13 septembre 2018 - 07:53:10


Fichiers éditeurs autorisés sur une archive ouverte



Francisco Massa, Renaud Marlet, Mathieu Aubry. Crafting a multi-task CNN for viewpoint estimation. British Machine Vision Conference (BMVC 2016), Sep 2016, York, United Kingdom. ⟨10.5244/C.30.91⟩. ⟨hal-01743267⟩



Consultations de la notice


Téléchargements de fichiers