Improving Neural Networks using Slice Models for Similar Classes

Jinwook Kim, Min-Soo Kim

Abstract: Under the traditional machine learning that optimizes overall accuracy, the accuracy of a model for similar classes tends to be lower than for other classes. In this paper, we propose a method that can improve the accuracy of such problematic similar classes by adopting the concept of slices. The proposed method can improve the accuracy of slices effectively without degrading the overall accuracy.