Sensitivity of Modern Deep Learning Neural Networks to Unbalanced Datasets in Multiclass Classification Problems

Sensitivity of Modern Deep Learning Neural Networks to Unbalanced Datasets in Multiclass Classification Problems

One of the critical problems in multiclass classification tasks is the imbalance of the dataset. This is especially true when using contemporary pre-trained neural networks, where the last layers of the neural network are retrained. Therefore, large datasets with highly unbalanced classes are not go...

Full description

Bibliographic Details
Main Authors: Marina Barulina, Sergey Okunkov, Ivan Ulitin, Askhat Sanbaev
Format: Article
Language:English
Published: MDPI AG 2023-07-01
Series:Applied Sciences
Subjects:
deep learning
unbalanced dataset
augmentation
multiclass classification
metrics boosting method
sota algorithm
Online Access:https://www.mdpi.com/2076-3417/13/15/8614

Internet

https://www.mdpi.com/2076-3417/13/15/8614

Similar Items