Additive Margin Softmax for Face Verification
Lists
Only you see this
Abstract
In this letter, we propose a conceptually simple and intuitive learning objective function, i.e., additive margin softmax, for face verification. In general, face verification tasks can be viewed as metric learning problems, even though lots of face verification models are trained in classification schemes. It is possible when a large-margin strategy is introduced into the classification model to encourage intraclass variance minimization. As one alternative, angular softmax has been proposed to incorporate the margin. In this letter, we introduce another kind of margin to the softmax loss function, which is more intuitive and interpretable. Experiments on LFW and MegaFace show that our algorithm performs better when the evaluation criteria are designed for very low false alarm rate.
BibTeX
@article{wang2018additive,
author = {Feng Wang and Jian Cheng and Weiyang Liu and Haijun Liu},
title = {{Additive Margin Softmax for Face Verification}},
journal = {IEEE Signal Processing Letters},
year = {2018},
url = {https://openreview.net/forum?id=DDZHtLUt9o},
}