my problem is : i have a neural network U-Net, but to do the segmentation on my sparse annotation, i need to implement the loss function for the imbalanced classes so the article says, that there is a method where they apply 2 approaches : instance based balancing, mini-batch based balancing
i would love to understand more about these 2 approaches and how to implement them in my neural network ??
can anyone help please ?
PS: i'm a beginner, but i'm so motivated and really want to understand how it works !!