If you take the following sentence from an article on deep neural networks

to regularize the classifier layer by estimating the marginalized effect of label-dropout during training.

What does label-dropout mean

  • 1
    $\begingroup$ For understanding that, you must understand what a drop out mean. This would help you with that :) $\endgroup$
    – Dawny33
    Feb 21 '16 at 15:51
  • $\begingroup$ Care to help explain drop out $\endgroup$
    – Michael
    Feb 22 '16 at 19:06

I ended up finding the paper you were referencing, maybe next time, add it to your post.

From what I can understand in this paper, label-dropout means that you are dropping the real labels and replace them with others.

The section of the paper you're referring to is explaining everything in great detail, so I'd try to read it carefully. In short, instead of using the ground-truth distribution (i.e. one 1 and a bunch of 0s) in the target layer, they are adding some uncertainty. That way, the model becomes less confident, and therefore is less prone to overfitting and becomes more adaptable.


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.