Deep Learning for Document Layout Generation: A First Reproducible Quantitative Evaluation and a Baseline Model - Equipe RFAI du Laboratoire Informatique de Tours Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Deep Learning for Document Layout Generation: A First Reproducible Quantitative Evaluation and a Baseline Model

Résumé

Deep generative models have been recently experimented in automated document layout generation, which led to significant qualitative results, assessed through user studies and displayed visuals. However, no reproducible quantitative evaluation has been settled in these works, which prevents scientific comparison of upcoming models with previous models. In this context, we propose a fully reproducible evaluation method and an original and efficient baseline model. Our evaluation protocol is meticulously defined in this work, and backed with an open source code available on this link.
Fichier principal
Vignette du fichier
icdar.pdf (1.3 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03385806 , version 1 (19-10-2021)

Identifiants

Citer

Romain Carletto, Hubert Cardot, Nicolas Ragot. Deep Learning for Document Layout Generation: A First Reproducible Quantitative Evaluation and a Baseline Model. 16th International Conference on Document Analysis and Recognition 2021, Sep 2021, Lausanne, Switzerland. pp.20 - 35, ⟨10.1007/978-3-030-86334-0_2⟩. ⟨hal-03385806⟩
115 Consultations
178 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More