Assessing hierarchies by their consistent segmentations - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Assessing hierarchies by their consistent segmentations

Résumé

Recent segmentation approaches start by creating a hierarchy of nested image partitions, and then specify a segmentation from it, usually, by choosing one horizontal cut. Our first contribution is to describe several different ways, some of them new, for specifying segmentations using the hierarchy regions. Then we consider the best hierarchy-induced segmentation, in which the segments are specified by a limited number, k, of hierarchy nodes/regions. The number of hierarchy-induced segmentations grows exponentially with the hierarchy size, implying that exhaustive search is unfeasible. We focus on a common quality measure, the Jaccard index (known also as IoU). Optimizing the Jaccard index is highly nontrivial. Yet, we propose an efficient optimization approach for exactly optimizing it. We found that the obtainable segmentation quality varies significantly depending on the way that the segments are specified by the hierarchy regions, and that representation of segmentation by only a few hierarchy nodes is often possible. (Code is available).
Fichier principal
Vignette du fichier
hierarchy_based_segmentation.pdf (2.17 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03633805 , version 1 (08-04-2022)
hal-03633805 , version 2 (06-12-2023)

Identifiants

Citer

Zeev Gutman, Ritvik Vij, Laurent Najman, Michael Lindenbaum. Assessing hierarchies by their consistent segmentations. 2022. ⟨hal-03633805v1⟩
343 Consultations
102 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More