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

Author(s)

Espadoto, Mateus ; Hirata, Nina ; Telea, Alexandru ; Hurter, C ; Purchase, H ; Braz, J ; Bouatouch, K

• Document type: Journal article
• Source: VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP; v. N/A, p. 11-pg., 2021-01-01.

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. (AU)

• FAPESP's process: 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery
• Grantee: Roberto Marcondes Cesar Junior
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 17/25835-9 - Understanding images and deep learning models
• Grantee: Nina Sumiko Tomita Hirata
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE