Pseudo-Feature Generation for Imbalanced Data Analysis in Deep Learning

07/17/2018
by   Tomohiko Konno, et al.
0

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 problems

READ FULL TEXT
02/18/2021

CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

Semi-supervised learning on class-imbalanced data, although a realistic ...
01/06/2020

Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning

We investigate learning a ConvNet classifier with class-imbalanced data....
12/24/2018

Feature Maps: A Comprehensible Software Representation for Design Pattern Detection

Design patterns are elegant and well-tested solutions to recurrent softw...
04/05/2021

Procrustean Training for Imbalanced Deep Learning

Neural networks trained with class-imbalanced data are known to perform ...
08/27/2019

Deep Learning-Based Strategy for Macromolecules Classification with Imbalanced Data from Cellular Electron Cryotomography

Deep learning model trained by imbalanced data may not work satisfactori...
07/26/2022

Distribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification

To address the trade-off problem of quality-diversity for the generated ...
02/09/2018

Deep Learning for Malicious Flow Detection

Cyber security has grown up to be a hot issue in recent years. How to id...