Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering

Clustering is among the most fundamental tasks in computer vision and machine learning. In this paper, we propose Variational Deep Embedding (VaDE), a novel unsupervised generative clustering approach within the framework of Variational Auto-Encoder (VAE). Specifically, VaDE models the data generati...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2017-06
Hauptverfasser:	Jiang, Zhuxi, Yin, Zheng, Tan, Huachun, Tang, Bangsheng, Hanning Zhou
Format:	Artikel
Sprache:	eng
Schlagworte:	Bayesian analysis Clustering Computer vision Embedding Lower bounds Machine learning Neural networks Probabilistic models
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!