Homological assessment of data representations - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Proceedings of SPIE, the International Society for Optical Engineering Année : 2022

Homological assessment of data representations

Résumé

In this paper we discuss the concept of the Cross-Barcode (P,Q) introduced and studied in the recent work [1]. In particular, we describe the emergence of this concept from the combinatorics of matrices of the pairwise distances between the two data representations. We also illustrate the applications of the Cross-Barcode (P,Q) to the evaluation of disentanglement in data representations. Experiments are carried out with the dSprites dataset from computer vision.
Fichier principal
Vignette du fichier
Homological Assessment of Data Representations.pdf (121.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03816596 , version 1 (17-10-2022)

Identifiants

Citer

Serguei Barannikov, Ilya Trofimov, Ekaterina Trimbach, Jun Wang, Evgeny Burnaev. Homological assessment of data representations. Proceedings of SPIE, the International Society for Optical Engineering, 2022, pp.41. ⟨10.1117/12.2623460⟩. ⟨hal-03816596⟩
15 Consultations
58 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More