Passer à la navigation principale Passer à la recherche Passer au contenu principal

TransVLAD: Multi-Scale Attention-Based Global Descriptors for Visual Geo-Localization

  • Yifan Xu
  • , Pourya Shamsolmoali
  • , Eric Granger
  • , Claire Nicodeme
  • , Laurent Gardes
  • , Jie Yang
  • Shanghai Jiao Tong University
  • East China Normal University
  • SNCF

Résultats de recherche: Chapitre dans un livre, rapport, actes de conférence › Participation à un ouvrage collectif lié à un colloque ou une conférence › Revue par des pairs

41 Citations (Scopus)

Résumé

Visual geo-localization remains a challenging task due to variations in the appearance and perspective among captured images. This paper introduces an efficient TransVLAD module, which aggregates attention-based feature maps into a discriminative and compact global descriptor. Unlike existing methods that generate feature maps using only convolutional neural networks (CNNs), we propose a sparse transformer to encode global dependencies and compute attention-based feature maps, which effectively reduces visual ambiguities that occurs in large-scale geo-localization problems. A positional embedding mechanism is used to learn the corresponding geometric configurations between query and gallery images. A grouped VLAD layer is also introduced to reduce the number of parameters, and thus construct an efficient module. Finally, rather than only learning from the global descriptors on entire images, we propose a self-supervised learning method to further encode more information from multi-scale patches between the query and positive gallery images. Extensive experiments on three challenging large-scale datasets indicate that our model outperforms state-of-the-art models, and has lower computational complexity. The code is available at: https://github.com/wacv-23/TVLAD.

Langue originaleAnglais
titreProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
EditeurInstitute of Electrical and Electronics Engineers Inc.
Pages2839-2848
Nombre de pages10
ISBN (Electronique)9781665493468
Les DOIs
ÉtatPublié - 2023
Evénement23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 - Waikoloa, Etats-Unis
Durée: 3 janv. 2023 → 7 janv. 2023

Série de publications

NomProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023

Conférence

Conférence23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
Pays/TerritoireEtats-Unis
La villeWaikoloa
Période3/01/23 → 7/01/23

Classification disciplinaire ASJC Scopus

  • Intelligence artificielle
  • Applications de l'informatique
  • Vision par ordinateur et reconnaissance de formes

Empreinte digitale

Voici les principaux termes ou expressions associés à « TransVLAD: Multi-Scale Attention-Based Global Descriptors for Visual Geo-Localization ». Ces libellés thématiques sont générés à partir du titre et du résumé de la publication. Ensemble, ils forment une empreinte digitale unique.

Citer cette ressource