How to train net with high class imbalance?
13 views (last 30 days)
Show older comments
Carlos Loredo López-Morago
on 11 Jul 2019
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 Comments
Accepted Answer
Kenta
on 11 Jul 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 Comments
More Answers (0)
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!