Authors:
Bárbara Benato
1
;
Alexandre Falcão
1
and
Alexandru-Cristian Telea
2
Affiliations:
1
Laboratory of Image Data Science, Institute of Computing, University of Campinas, Campinas, Brazil
;
2
Department of Information and Computing Sciences, Faculty of Science, Utrecht University, Utrecht, The Netherlands
Keyword(s):
Data Separation, Visual Separation, Semi-supervised Learning, Embedded Pseudo-labeling, Contrastive Learning, Image Classification.
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.
(More)