Label Smoothing

Label Smoothing Redistributes Target Probability Across Classes

A classifier trained with one-hot targets assigns all target probability mass to one class. Label smoothing changes that target before cross-entropy is evaluated: some mass is moved away from the designated class and assigned to other classes. The network architecture can remain identical, yet the optimization objective is no longer the same. That distinction matters when interpreting confidence, loss values, and implementation settings. Label smoothing is not a post-processing operation on predicted probabilities. It changes the target distribution used to produce the training signal.