Cavity Filling: Pseudo-Feature Generation for Multi-Class Imbalanced Data Problems in Deep Learning
arXiv:1807.06538
Abstract
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.
arXiv commentThe slides are available at https://goo.gl/SPsSDh in English and at https://goo.gl/RFHYAa in Japanese. 9 pages
References in corpus (6)
- SMOTE: Synthetic Minority Over-sampling Technique
- A systematic study of the class imbalance problem in convolutional neural networks
- Learning to Reweight Examples for Robust Deep Learning
- BAGAN: Data Augmentation with Balancing GAN
- A Cost-Sensitive Deep Belief Network for Imbalanced Classification
- Building Disease Detection Algorithms with Very Small Numbers of Positive Samples