[2A1] [General Session] 2. Machine Learning

[2A1-04] Pseudo-feature generation from feature map in deep learning for imbalanced data multi-class image classification

〇Tomohiko Konno¹, Hideaki Fujii¹, Michiaki Iwazume¹ (1. AI Science R&D Promotion Center in National Institute of Information and Communication Technology )

Keywords:Pseudo feature generation, Deep learning, Imbalanced data, Image Classification

If some classes of the data have an only small number of samples, the accuracies of the classes become too low. It is well known as an imbalanced data problem. We often encounter imbalanced data in reality. In a sense, all the wild data are imbalanced.

In this paper, we make pseudo-feature from feature map in lower layers of deep neural networks, and we augment the data of minor classes to improve the imbalanced-data problem. We compare our proposed method with existing ones in imbalanced data multi-class image classification problems.