Unbalancing Datasets to Enhance CNN Models Learnability: A Class-Wise Metrics-Based Closed-Loop Strategy Proposal

Unbalancing Datasets to Enhance CNN Models Learnability: A Class-Wise Metrics-Based Closed-Loop Strategy Proposal

Developing deep learning models often involves working with balanced datasets. However, in real-world scenarios, class equilibrium is rarely observed. To address this, oversampling and undersampling techniques are commonly employed, with appropriate monitoring and countermeasures to mitigate the ris...

Full description

Saved in:
Bibliographic Details
Main Authors: Somayeh Shahrabadi, Victor Alves, Emanuel Peres, Raul Morais Dos Santos, Telmo Adao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Deep learning
convolutional neural networks (CNNs)
class imbalance
closed-loop optimization
data augmentation
GAN-based augmentation
Online Access:https://ieeexplore.ieee.org/document/10938149/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10938149/

Similar Items