Pseudo-Feature Generation for Imbalanced Data Analysis in Deep Learning
Authors:
Preprint
Abstract
We generate pseudo-features by multivariate probability distributions obtained from feature maps in a low layer of trained deep neural networks. Then, we virtually augment the data of minor classes by the pseudo-features in order to overcome imbalanced data problems. Because all the wild data are imbalanced, the proposed method has the possibility to improve the ability of DNN in a broad range of problemsKeywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings2019
- Instance selection improves geometric mean accuracy: a study on imbalanced data classificationProgress in Artificial Intelligence, 2019
- Building Disease Detection Algorithms with Very Small Numbers of Positive Samples2017
- Learning from imbalanced data: open challenges and future directionsProgress in Artificial Intelligence, 2016
- Vehicle detection in aerial imagery : A small target detection benchmarkJournal of Visual Communication and Image Representation, 2016
- Evolutionary undersampling boosting for imbalanced classification of breast cancer malignancyApplied Soft Computing, 2016
- Adaptive weighted imbalance learning with application to abnormal activity recognitionNeurocomputing, 2016
- Learned lessons in credit card fraud detection from a practitioner perspectiveExpert Systems with Applications, 2014
- Enhanced and hierarchical structure algorithm for data imbalance problem in semantic extraction under massive video datasetMultimedia Tools and Applications, 2012
- Class imbalance methods for translation initiation site recognition in DNA sequencesKnowledge-Based Systems, 2012