Label Smoothing as Another Regularization Trick
What is label smoothing and how to implement it in PyTorch
Published in
4 min readOct 29, 2021
Overfitting and probability calibration are two issues that arise when training deep learning models. There are a lot of regularization techniques in deep learning to address overfitting; weight decay, early stopping, and dropout are some of the most popular ones. On the other hand…