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.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
Loading...