Semantic alignment for multi-item compression - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Semantic alignment for multi-item compression

Résumé

Coding algorithms usually compress independently the images of a collection, in particular when the correlation between them only resides at the semantic level, i.e., information related to the high-level image content. In this work, we propose a coding solution able to exploit this semantic redundancy to decrease the storage cost of data collections. First we introduce the multi-item compression framework. Then we derive a loss term to shape the latent space of a variational auto-encoder so that the latent vectors of semantically identical images can be aligned. Finally, we experimentally demonstrate that this alignment leads to a more compact representation of the data collection.
Fichier principal
Vignette du fichier
Papier_ICIP.pdf (2.98 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03760650 , version 1 (25-08-2022)

Identifiants

  • HAL Id : hal-03760650 , version 1

Citer

Tom Bachard, Anju Jose Tom, Thomas Maugey. Semantic alignment for multi-item compression. ICIP 2022 - IEEE International Conference on Image Processing, Oct 2022, Bordeaux, France. pp.1-5. ⟨hal-03760650⟩
92 Consultations
50 Téléchargements

Partager

Gmail Facebook X LinkedIn More