Linking Data Separation, Visual Separation, and Classifier Performance Using Pseudo-labeling by Contrastive Learning

Bárbara Benato, Alexandre Falcão, Alexandru-Cristian Telea

2023

Abstract

Lacking supervised data is an issue while training deep neural networks (DNNs), mainly when considering medical and biological data where supervision is expensive. Recently, Embedded Pseudo-Labeling (EPL) addressed this problem by using a non-linear projection (t-SNE) from a feature space of the DNN to a 2D space, followed by semi-supervised label propagation using a connectivity-based method (OPFSemi). We argue that the performance of the final classifier depends on the data separation present in the latent space and visual separation present in the projection. We address this by first proposing to use contrastive learning to produce the latent space for EPL by two methods (SimCLR and SupCon) and by their combination, and secondly by showing, via an extensive set of experiments, the aforementioned correlations between data separation, visual separation, and classifier performance. We demonstrate our results by the classification of five real-world challenging image datasets of human intestinal parasites with only 1% supervised samples.

Paper Citation

in Harvard Style

Benato B., Falcão A. and Telea A. (2023). Linking Data Separation, Visual Separation, and Classifier Performance Using Pseudo-labeling by Contrastive Learning. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 315-324. DOI: 10.5220/0011856300003417

in Bibtex Style

@conference{visapp23,
author={Bárbara Benato and Alexandre Falcão and Alexandru-Cristian Telea},
title={Linking Data Separation, Visual Separation, and Classifier Performance Using Pseudo-labeling by Contrastive Learning},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={315-324},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011856300003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Linking Data Separation, Visual Separation, and Classifier Performance Using Pseudo-labeling by Contrastive Learning
SN - 978-989-758-634-7
AU - Benato B.
AU - Falcão A.
AU - Telea A.
PY - 2023
SP - 315
EP - 324
DO - 10.5220/0011856300003417
PB - SciTePress