Communication Dans Un Congrès Année : 2019

Unsupervised Neural Segmentation and Clustering for Unit Discovery in Sequential Data

Résumé

We study the problem of unsupervised segmentation and clustering of handwritten lines with applications to character discovery. We propose a constrained variant of Vector Quantized Variational Autoencoder (VQ-VAE) which produces a discrete and piecewise-constant encoding of the data. We show that the constrained quantization task is dual to a Markovian dynamics prior placed on the latent codes. Such view facilitates a probabilistic interpretation of the constraints and allows efficient inference. We demonstrate the effectiveness of the proposed method in the context of unsupervised handwriting character discovery in 17th-century scanned manuscripts.

Fichier principal
Vignette du fichier
PGR009.pdf (291.17 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02399138 , version 1 (08-12-2019)

Licence

Identifiants

  • HAL Id : hal-02399138 , version 1

Citer

Jan Chorowski, Nanxin Chen, Ricard Marxer, Hans J G A Dolfing, Adrian Łańcucki, et al.. Unsupervised Neural Segmentation and Clustering for Unit Discovery in Sequential Data. NeurIPS 2019 workshop - Perception as generative reasoning - Structure, Causality, Probability, Dec 2019, Vancouver, Canada. ⟨hal-02399138⟩
724 Consultations
971 Téléchargements

Partager

  • More