Herein, we generate pseudo-features based on the multivariate probability distributions obtained from the feature maps in layers of trained deep neural networks. Further, we augment the minor-class data based on these generated pseudo-features to overcome the imbalanced data problems. The proposed method, i.e., cavity filling, improves the deep learning capabilities in several problems because all the real-world data are observed to be imbalanced.
@article{arxiv.1807.06538,
title = {Cavity Filling: Pseudo-Feature Generation for Multi-Class Imbalanced Data Problems in Deep Learning},
author = {Tomohiko Konno and Michiaki Iwazume},
journal= {arXiv preprint arXiv:1807.06538},
year = {2019}
}
Comments
The slides are available at https://goo.gl/SPsSDh in English and at https://goo.gl/RFHYAa in Japanese. 9 pages