How to train net with high class imbalance?

13 次查看（过去 30 天）
Carlos Loredo López-Morago
回答： Kenta 2020-7-11
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.

请先登录，再回答此问题。

采纳的回答

Kenta
Kenta 2020-7-11
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.
https://jp.mathworks.com/matlabcentral/fileexchange/78020-oversampling-for-deep-learning-classification-example

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by