Hyperbolic Variational Auto-Encoder for Remote Sensing Embeddings - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Hyperbolic Variational Auto-Encoder for Remote Sensing Embeddings

Résumé

The computer vision community is increasingly interested in exploring hyperbolic space for image representation, as hyperbolic approaches have demonstrated outstanding results in efficiently representing data with an underlying hierarchy. This interest arises from the intrinsic hierarchical nature among images. However, despite the hierarchical nature of remote sensing (RS) images, the investigation of hyperbolic spaces within the RS community has been relatively limited. The objective of this study is therefore to examine the relevance of hyperbolic embeddings of RS data, focusing on scene embedding. Using a Variational Auto-Encoder, we project the data into a hyperbolic latent space while ensuring numerical stability with a feature clipping technique. Experiments conducted on the NWPU-RESISC45 image dataset demonstrate the superiority of hyperbolic embeddings over the Euclidean counterparts in a classification task. Our study highlights the potential of operating in hyperbolic space as a promising approach for embedding RS data.
Fichier principal
Vignette du fichier
IGARSS23_HVAE_FullPapaer.pdf (1.25 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04159375 , version 1 (11-07-2023)

Identifiants

  • HAL Id : hal-04159375 , version 1

Citer

Manal Hamzaoui, Laetitia Chapel, Minh-Tan Pham, Sébastien Lefèvre. Hyperbolic Variational Auto-Encoder for Remote Sensing Embeddings. International Geoscience and Remote Sensing Symposium, Jul 2023, Pasadena (California), United States. ⟨hal-04159375⟩
57 Consultations
63 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More