How to train net with high class imbalance?
14 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Carlos Loredo López-Morago
el 11 de Jul. de 2019
Respondida: Kenta
el 11 de Jul. de 2020
Hi, I am doing a semantic segmentation that has a large difference between the two classes. So that, it tends to overpredict when I train the network. Is there any way to train the network specifically in one of the classes?
I am using classweights already, but as most of the pictures is background, the training accuracy tends to increase and the loss to decrease until constant, which generates zero accuracy when testing in the most important but imbalanced class.
0 comentarios
Respuesta aceptada
Kenta
el 11 de Jul. de 2020
Over-sampling can be one solution for that task. Copy the image of smaller classes so that the number of images in each class can balance and perform training using data augmentation function.
0 comentarios
Más respuestas (0)
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!