A Novel Framework for Deep Learning from Pairwise Constraints

Authors

Wubin Sheng, Portland State UniversityFollow
John Lipor, Portland State UniversityFollow

Published In

2020 54th Asilomar Conference on Signals, Systems, and Computers

Document Type

Citation

Publication Date

11-1-2020

Abstract

We consider the problem of deep semi-supervised classification, where label information is obtained in the form of pairwise constraints. Existing approaches to this problem begin with a clustering network and utilize custom loss functions to encourage the learned representations to conform to the obtained constraints. We present a novel framework that seamlessly integrates pairwise constrained clustering, semi-supervised classification, and supervised classification. This approach leverages advances in unsupervised learning by jointly training a Siamese network and autoencoder to learn a representation that is amenable for both clustering and classification. The resulting framework outperforms existing approaches on common image recognition datasets.

Rights

©2020 IEEE

Locate the Document

https://doi.org/10.1109/IEEECONF51394.2020.9443499

DOI

10.1109/IEEECONF51394.2020.9443499

Persistent Identifier

https://archives.pdx.edu/ds/psu/36002

Publisher

IEEE

Citation Details

Sheng, W., & Lipor, J. (2020). A Novel Framework for Deep Learning from Pairwise Constraints. Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ieeeconf51394.2020.9443499