Clustering-Driven Deep Embedding With Pairwise Constraints

Sharon Fogel, Hadar Averbuch-Elor, Daniel Cohen-Or, Jacob Goldberger

Research output: Contribution to journalArticlepeer-review

29 Scopus citations

Abstract

Recently, there has been increasing interest to leverage the competence of neural networks to analyze data. In particular, new clustering methods that employ deep embeddings have been presented. In this paper, we depart from centroid-based models and suggest a new framework, called Clustering-driven deep embedding with PAirwise Constraints (CPAC), for nonparametric clustering using a neural network. We present a clustering-driven embedding based on a Siamese network that encourages pairs of data points to output similar representations in the latent space. Our pair-based model allows augmenting the information with labeled pairs to constitute a semi-supervised framework. Our approach is based on analyzing the losses associated with each pair to refine the set of constraints. We show that clustering performance increases when using this scheme, even with a limited amount of user queries. We demonstrate how our architecture is adapted for various types of data and present the first deep framework to cluster three-dimensional (3-D) shapes.

Original languageEnglish
Article number8739140
Pages (from-to)16-27
Number of pages12
JournalIEEE Computer Graphics and Applications
Volume39
Issue number4
DOIs
StatePublished - 1 Jul 2019
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Funding

Daniel Cohen-Or is a Professor with the School of Computer Science, Tel-Aviv University, Tel Aviv, Israel. He was the recipient of the Eurographics Outstanding Technical Contributions award in 2005, and ACM SIGGRAPH Computer Graphics Achievement Award in 2018. In 2015, he was named a Thomson Reuters Highly Cited Researcher. His main interests are in a few areas: image synthesis, analysis and reconstruction, motion and transformations, and shapes and surfaces. He received the B.Sc. (cum laude) degree in mathematics and computer science and the M.Sc. (cum laude) degree in computer science, both from Ben-Gurion University, Beer-sheba, Israel, in 1985 and 1986, respectively, and the Ph.D. degree from the Department of Computer Science, State University of New York at Stony Brook, Stony Brook, NY, USA, in 1991. Contact him at [email protected].

FundersFunder number
Anacostia Community Museum

    Fingerprint

    Dive into the research topics of 'Clustering-Driven Deep Embedding With Pairwise Constraints'. Together they form a unique fingerprint.

    Cite this