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 (12)

• Auto-Encoding Variational Bayes
• EMNIST: an extension of MNIST to handwritten letters
• Adaptive Computation Time for Recurrent Neural Networks
• Variational Lossy Autoencoder
• On Constrained Spectral Clustering and Its Applications
• Clustering with Deep Learning: Taxonomy and New Methods
• Unsupervised Deep Embedding for Clustering Analysis
• Multi-class Classification without Multi-class Labels
• Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
• Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
• User Experience of the CoSTAR System for Instruction of Collaborative Robots
• Neural Clustering Processes

Cited by in corpus (6)

• Transformers in Vision: A Survey
• Labelling unlabelled videos from scratch with multi-modal self-supervision
• Amortized Variational Inference: A Systematic Review
• Neural Clustering Processes
• Attention-Based Clustering: Learning a Kernel from Context
• You Never Cluster Alone