| Full text | |
| Author(s): |
Benato, Barbara C.
;
Telea, Alexandru C.
;
Falcao, Alexandre X.
Total Authors: 3
|
| Document type: | Journal article |
| Source: | PATTERN RECOGNITION; v. 141, p. 16-pg., 2023-05-05. |
| Abstract | |
The absence of large annotated datasets to train deep neural networks (DNNs) is an issue since manual annotation is time-consuming, expensive, and error-prone. Semi-supervised learning techniques can ad-dress the problem propagating pseudo labels from supervised to unsupervised samples. However, they still require training and validation sets with many supervised samples. This work proposes a methodol-ogy, namely Deep Feature Annotation (DeepFA), that dismisses the validation set and uses very few super-vised samples (e.g., 1% of the dataset). DeepFA modifies the feature spaces of a DNN along with meta-pseudo-labeling iterations in a 2D non-linear projection space using the most confidently labeled samples of an optimum-path forest semi-supervised classifier. We present a comprehensive study on DeepFA and a new variant that detects the best DNN model for generalization during the pseudo-labeling iterations. We evaluate components of DeepFA on eight datasets, finding the best DeepFA approach and showing that it outperforms self-pseudo-labeling.(c) 2023 Elsevier Ltd. All rights reserved. (AU) | |
| FAPESP's process: | 22/12668-5 - Exploring visual analytics for supporting the user in active learning |
| Grantee: | Bárbara Caroline Benato |
| Support Opportunities: | Scholarships abroad - Research Internship - Doctorate |