Semi-supervised learning with connectivity-driven convolutional neural networks
The annotation of large datasets is an issue whose challenge increases as the number of labeled samples available to train the classifier reduces in comparison to the amount of unlabeled data. In this context, semi-supervised learning methods aim at discovering and propagating labels to unlabeled sa...
| Autores: | , , , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2019 |
| País: | Brasil |
| Institución: | Universidade Estadual Paulista (UNESP) |
| Repositorio: | Repositório Institucional da UNESP |
| Idioma: | inglés |
| OAI Identifier: | oai:repositorio.unesp.br:11449/190583 |
| Acceso en línea: | http://dx.doi.org/10.1016/j.patrec.2019.08.012 http://hdl.handle.net/11449/190583 |
| Access Level: | acceso abierto |
| Palabra clave: | Convolutional neural networks Optimum-path forest Semi-supervised learning |
| Sumario: | The annotation of large datasets is an issue whose challenge increases as the number of labeled samples available to train the classifier reduces in comparison to the amount of unlabeled data. In this context, semi-supervised learning methods aim at discovering and propagating labels to unlabeled samples, such that their correct labeling can improve the classification performance. In this work, we propose a semi-supervised methodology that explores the optimum connectivity among unlabeled samples through the Optimum-Path Forest (OPF) classifier to improve the learning process of Convolution Neural Networks (CNNs). Our proposal makes use of the OPF to classify an unlabeled training set that is used to pre-train a CNN for further fine-tuning using the limited labeled data only. The proposed approach is experimentally validated on traditional datasets and provides competitive results in comparison to state-of-the-art semi-supervised learning methods. |
|---|