Self-supervised Dimensionality Reduction with Neural Networks and Pseudo-labeling

Mateus Espadoto, Mateus Espadoto, Nina Hirata, Alexandru Telea

Abstract

Dimensionality reduction (DR) is used to explore high-dimensional data in many applications. Deep learning techniques such as autoencoders have been used to provide fast, simple to use, and high-quality DR. However, such methods yield worse visual cluster separation than popular methods such as t-SNE and UMAP. We propose a deep learning DR method called Self-Supervised Network Projection (SSNP) which does DR based on pseudo-labels obtained from clustering. We show that SSNP produces better cluster separation than autoencoders, has out-of-sample, inverse mapping, and clustering capabilities, and is very fast and easy to use.

Download


Paper Citation


in Harvard Style

Espadoto M., Hirata N. and Telea A. (2021). Self-supervised Dimensionality Reduction with Neural Networks and Pseudo-labeling.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: IVAPP, ISBN 978-989-758-488-6, pages 27-37. DOI: 10.5220/0010184800270037


in Bibtex Style

@conference{ivapp21,
author={Mateus Espadoto and Nina Hirata and Alexandru Telea},
title={Self-supervised Dimensionality Reduction with Neural Networks and Pseudo-labeling},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: IVAPP,},
year={2021},
pages={27-37},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010184800270037},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: IVAPP,
TI - Self-supervised Dimensionality Reduction with Neural Networks and Pseudo-labeling
SN - 978-989-758-488-6
AU - Espadoto M.
AU - Hirata N.
AU - Telea A.
PY - 2021
SP - 27
EP - 37
DO - 10.5220/0010184800270037