TY - GEN

T1 - On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering

AU - Trosten, Daniel J.

AU - Lokse, Sigurd

AU - Jenssen, Robert

AU - Kampffmeyer, Michael C.

N1 - Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - 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 Deep-MVC, 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 components11Code: https://github.com/DanielTrosten/DeepMVC.

AB - 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 Deep-MVC, 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 components11Code: https://github.com/DanielTrosten/DeepMVC.

KW - Multi-modal learning

UR - http://www.scopus.com/inward/record.url?scp=85167841631&partnerID=8YFLogxK

U2 - 10.1109/CVPR52729.2023.02296

DO - 10.1109/CVPR52729.2023.02296

M3 - Article in proceedings

AN - SCOPUS:85167841631

SP - 23976

EP - 23985

BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

PB - IEEE Computer Society Press

T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

Y2 - 18 June 2023 through 22 June 2023

ER -