How do you handle unbalanced image datasets?

Question

I have an image data set on which I am training a CNN. The data set is slightly unbalanced. So, my solution up till now was to delete some images of the majority class.

But I now realize that there are cleaner ways to deal with this. But I haven't been able to find ways to fix unbalanced image data sets. Only structured data-sets.

I would like someone to guide me to fix the unbalance, other than deleting data from the majority class.

Answer 1

You can always adjust class weights accordingly. I know the reference is not for image data but it shouldn't matter if you are doing classification. Here is another answer more direct to the point.