PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions

Zhaoqi Leng, Mingxing Tan, Chenxi Liu, Ekin Dogus Cubuk, Jay Shi, Shuyang Cheng, Dragomir Anguelov

Abstract: Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can take on much more...