Regularization method Label Smoothing

Label smoothing is a regularization method, which smooths the real one-hot label such as [0,1] and moves closer to the "middle", such as becoming [0.05, 0.95], so that the trained model will not be excessive Confidence, improve generalization ability.

reference:

Label Smoothing label smoothing (Label smooth regularization, LSR)_hxxjxw's blog-CSDN blog_label smoothing loss

[Regularization] Detailed Explanation of Label Smoothing_Yao Luyaoyao's Blog-CSDN Blog_label smoothing 

Detailed Explanation of Label Smoothing 

Label smoothing label smoothing_Braylon1002's Blog-CSDN Blog_label smoothing 

Guess you like

Origin blog.csdn.net/qq_41021141/article/details/126254707