You Never Cluster Alone

Abstract

Recent advances in self-supervised learning with instance-level contrastive objectives facilitate unsupervised clustering. However, a standalone datum is not perceiving the context of the holistic cluster, and may undergo sub-optimal assignment. In this paper, we extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation that encodes the context of each data group. Contrastive learning with this representation then rewards the assignment of each datum. To implement this vision, we propose twin-contrast clustering (TCC). We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. On one hand, with the corresponding assignment variables being the weight, a weighted aggregation along the data points implements the set representation of a cluster. We further propose heuristic cluster augmentation equivalents to enable cluster-level contrastive learning. On the other hand, we derive the evidence lower-bound of the instance-level contrastive objective with the assignments. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps. Extensive experiments show that TCC outperforms the state-of-the-art on challenging benchmarks.

NeurIPS 2021

References in corpus (12)

• Distilling the Knowledge in a Neural Network
• Semi-Supervised Learning with Deep Generative Models
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• SPICE: Semantic Pseudo-labeling for Image Clustering
• Deep Discriminative Clustering Analysis
• Deep Unsupervised Clustering Using Mixture of Autoencoders
• Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation
• Deep Amortized Clustering
• Deep Clustering by Semantic Contrastive Learning
• Improving Unsupervised Image Clustering With Robust Learning