Deep Amortized Clustering

Abstract

We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points into clusters, and how to count the number of clusters in datasets. DAC is meta-learned using labelled datasets for training, a process distinct from traditional clustering algorithms which usually require hand-specified prior knowledge about cluster shapes/structures. We empirically show, on both synthetic and image data, that DAC can efficiently and accurately cluster new datasets coming from the same distribution used to generate training datasets.

References in corpus (5)

• EMNIST: an extension of MNIST to handwritten letters
• Variational Lossy Autoencoder
• Multi-class Classification without Multi-class Labels
• Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
• User Experience of the CoSTAR System for Instruction of Collaborative Robots

Cited by in corpus (1)

• Attention-Based Clustering: Learning a Kernel from Context