Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval - Université de Lorraine Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval

Résumé

Most of the research in content-based image retrieval (CBIR) focus on developing robust feature representations that can effectively retrieve instances from a database of images that are visually similar to a query. However, the retrieved images sometimes contain results that are not semantically related to the query. To address this, we propose a method for CBIR that captures both visual and semantic similarity using a visual hierarchy. The hierarchy is constructed by merging classes with overlapping features in the latent space of a deep neural network trained for classification, assuming that overlapping classes share high visual and semantic similarities. Finally, the constructed hierarchy is integrated into the distance calculation metric for similarity search. Experiments on standard datasets: CUB-200-2011 and CIFAR100, and a real-life use case using diatom microscopy images show that our method achieves superior performance compared to the existing methods on image retrieval.
Fichier principal
Vignette du fichier
2308.08431.pdf (552.46 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04423201 , version 1 (22-02-2024)

Identifiants

Citer

Aishwarya Venkataramanan, Martin Laviale, Cédric Pradalier. Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval. Computer Vision Systems. ICVS 2023, Sep 2023, Vienne (AUT), Austria. pp.422-431, ⟨10.1007/978-3-031-44137-0_35⟩. ⟨hal-04423201⟩
14 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More