Solving Class Imbalance Problem in Target Detection with a Squared Cross Entropy Based Method.

The foreground-background class imbalance in target detection is inevitable, which is caused by the training data set. Specifically, the number of targets contained in any image of the training data set is generally very small, that is, the number of positive examples is small, while the number of the negative examples from the background is large. Therefore, the ability of the algorithm to detect the negatives is stronger than that of positive examples. The Focal Loss algorithm solves this problem by improving the classification loss function. However, Focal Loss brings additional hyper-parameters, which remains to be further adjusted. This paper refers to the idea of Focal Loss from the classification loss function, and proposes new a classification loss function SCE that is similar to Focal Loss but does not contain any extra hyper-parameters. Experiments in the paper prove that SCE can obtain performance equivalent to Focal Loss without introducing hyper-parameters.