Twin Contrastive Learning for Online Clustering

Abstract

This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster representation, respectively. Based on the observation, for a given dataset, the proposed TCL first constructs positive and negative pairs through data augmentations. Thereafter, in the row and column space of the feature matrix, instance- and cluster-level contrastive learning are respectively conducted by pulling together positive pairs while pushing apart the negatives. To alleviate the influence of intrinsic false-negative pairs and rectify cluster assignments, we adopt a confidence-based criterion to select pseudo-labels for boosting both the instance- and cluster-level contrastive learning. As a result, the clustering performance is further improved. Besides the elegant idea of twin contrastive learning, another advantage of TCL is that it could independently predict the cluster assignment for each instance, thus effortlessly fitting online scenarios. Extensive experiments on six widely-used image and text benchmarks demonstrate the effectiveness of TCL. The code will be released on GitHub.

References in corpus (20)

• Fast unfolding of communities in large networks
• Auto-Encoding Variational Bayes
• A Simple Framework for Contrastive Learning of Visual Representations
• Representation Learning with Contrastive Predictive Coding
• Distributed Representations of Sentences and Documents
• Bootstrap your own latent: A new approach to self-supervised Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• Improved Baselines with Momentum Contrastive Learning
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Prototypical Contrastive Learning of Unsupervised Representations
• Deep Clustering for Unsupervised Learning of Visual Features
• Big Self-Supervised Models are Strong Semi-Supervised Learners
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• Self-Taught Convolutional Neural Networks for Short Text Clustering
• SPICE: Semantic Pseudo-labeling for Image Clustering
• Self-labelling via simultaneous clustering and representation learning
• XAI Beyond Classification: Interpretable Neural Clustering
• Deep Discriminative Clustering Analysis
• Doubly Contrastive Deep Clustering

Cited by in corpus (7)

• Deep Multiview Clustering by Contrasting Cluster Assignments
• Learning Representation for Clustering via Prototype Scattering and Positive Sampling
• Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation
• A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery
• Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets
• Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection
• Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering