Cross-year multi-modal image retrieval using siamese networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès The 27th IEEE International Conference on Image Processing Année : 2020

Cross-year multi-modal image retrieval using siamese networks

Résumé

This paper introduces a multi-modal network that learns to retrieve by content vertical aerial images of French urban and rural territories taken about 15 years apart. This means it should be invariant against a big range of changes as the (nat-ural) landscape evolves over time. It leverages the original images and semantically segmented and labeled regions. The core of the method is a Siamese network that learns to extract features from corresponding image pairs across time. These descriptors are discriminative enough, such that a simple kNN classifier on top, suffices as final geo-matching criteria. The method outperformed SOTA "off-the-shelf" image descrip-tors GEM and ResNet50 on the new aerial images dataset.
Fichier principal
Vignette du fichier
ICIP_camera_ready.pdf (959.65 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02903434 , version 1 (21-07-2020)

Identifiants

Citer

Margarita Khokhlova, Valérie Gouet-Brunet, Nathalie Abadie, Liming Chen. Cross-year multi-modal image retrieval using siamese networks. ICIP 2020 – 27th IEEE International Conference on Image Processing, Oct 2020, Abou Dhabi, United Arab Emirates. ⟨10.1109/ICIP40778.2020.9190662⟩. ⟨hal-02903434⟩

Relations

206 Consultations
325 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More