2023/03/17 by Daniel J. Trosten, Trosten, Daniel J., Sigurd Løkse +5 · 4 citations
Computer Science · Mathematics · Psychology · #Advanced Clustering Algorithms Research #Artificial intelligence #Cluster analysis #Component (thermodynamics) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Data science #Deep learning #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Field (mathematics) #Leverage (statistics) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Mathematics #Openness to experience #Psychology #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2303.09877
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/03/17 · openalex created_date 2023/03/21 · openalex updated_date 2026/07/28
Self-supervised learning is a central component in recent approaches to deep multi-view clustering (MVC). However, we find large variations in the development of self-supervision-based methods for deep MVC, potentially slowing the progress of the field. To address this, we present DeepMVC, a unified framework for deep MVC that includes many recent methods as instances. We leverage our framework to make key observations about the effect of self-supervision, and in particular, drawbacks of aligning representations with contrastive learning. Further, we prove that contrastive alignment can negatively influence cluster separability, and that this effect becomes worse when the number of views increases. Motivated by our findings, we develop several new DeepMVC instances with new forms of self-supervision. We conduct extensive experiments and find that (i) in line with our theoretical findings, contrastive alignments decreases performance on datasets with many views; (ii) all methods benefit from some form of self-supervision; and (iii) our new instances outperform previous methods on several datasets. Based on our results, we suggest several promising directions for future research. To enhance the openness of the field, we provide an open-source implementation of DeepMVC, including recent models and our new instances. Our implementation includes a consistent evaluation protocol, facilitating fair and accurate evaluation of methods and components.