Share AI Models and Methods


AM-Softmax Loss is also called additive margin softmax. It is an improvement of softmax loss and proposed in paper: Additive Margin Softmax for Face Verification. This loss function often be used in face and speaker verification task.

AM-Softmax Loss Visualization

It is denoted as:

AM-Softmax Loss

You can find this loss in this page:

The effect of AM-Softmax

From this paper, we can find:

s = 30, the performance become the best when m = 0.35 to m = 0.4. We usually use it when s = 30 and m = 0.35

The effect of AM-Softmax