3
$\begingroup$

I have 22 classes of objects but they have very skewed distributions where max class has 100.000 images and the min class has 1600 images. In that setting I would like to hear some possible solutions to this balance problem.

I have tried followings so far;

  1. multiply number of instances in the lower classes up to the max class by replicating the instances, possibly adding some noise as well.

  2. changing the learning regarding the class distribution in the given minibatch of the next epoch. (no implemented but in my mind)

What are your suggestions?

$\endgroup$
1
$\begingroup$

You can also modify your cost function so that instances in the smaller class have more weight. This makes training computationally less demanding, when compared to your option 1.

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.