GO Loss: A Gaussian Distribution-Based Orthogonal Decomposition Loss for Classification

<div>Distributions of the features trained using (a) soft-max and (b) GO loss on MNIST. Each color represents a class. The GO loss has better intraclass compactness and interclass separation than traditional soft-max loss. Best viewed in color.</div>

Complexity

fig1

Figure 1

Figure 1: GO Loss: A Gaussian Distribution-Based Orthogonal Decomposition Loss for Classification 