I had a bit of a problem when reproducing the project. Could you explain the loss function (SmoothClsLoss) used in classification task? I didn't find an introduction to it in the paper.
Thanks for your interest in our work.
We apply label smoothing to the loss function. It is quite a common technique of training on classification task. If you are interested in the mechanism of it, I recommend this paper.
Thanks for your excellent works !
I had a bit of a problem when reproducing the project. Could you explain the loss function (SmoothClsLoss) used in classification task? I didn't find an introduction to it in the paper.