Object detection via a multi-region & semantic segmentation-aware CNN model

Abstract : We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. We exploit the above properties of our recognition module by integrating it on an iterative localization mechanism that alternates between scoring a box proposal and refining its location with a deep CNN regression model. Thanks to the efficient use of our modules, we detect objects with very high localization accuracy. On the detection challenges of PASCAL VOC2007 and PASCAL VOC2012 we achieve mAP of 78.2% and 73.9% correspondingly, surpassing any other published work by a significant margin.
Type de document :
Communication dans un congrès
ICCV 2015, Dec 2015, Santiago, Chile. ICCV 2015
Liste complète des métadonnées

Littérature citée [31 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01245664
Contributeur : Spyros Gidaris <>
Soumis le : jeudi 17 décembre 2015 - 14:58:16
Dernière modification le : mercredi 11 avril 2018 - 12:12:03
Document(s) archivé(s) le : vendredi 18 mars 2016 - 13:40:52

Fichier

1029.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01245664, version 1
  • ARXIV : 1505.01749

Citation

Spyros Gidaris, Nikos Komodakis. Object detection via a multi-region & semantic segmentation-aware CNN model. ICCV 2015, Dec 2015, Santiago, Chile. ICCV 2015. 〈hal-01245664〉

Partager

Métriques

Consultations de la notice

434

Téléchargements de fichiers

333