Deep learning

Sociology

Pattern recognition (psychology)

Metric (unit)

Feature (linguistics)

Social science

Margin (machine learning)

Discriminative model

Normalization (sociology)

Machine learning

Engineering

Philosophy

Artificial intelligence

Softmax function

Anthropology

Operations management

Face (sociological concept)

Facial recognition system

Computer science

Linguistics

Feature extraction

IEEE Signal Processing Letters

In this paper, we propose a conceptually simple and geometrically interpretable objective function, i.e. additive margin Softmax (AM-Softmax), for deep face verification. In general, the face verification task can be viewed as a metric learning problem, so learning large-margin face features whose intra-class variation is small and inter-class difference is large is of great importance in order to achieve good performance. Recently, Large-margin Softmax and Angular Softmax have been proposed to incorporate the angular margin in a multiplicative manner. In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works. We also emphasize and discuss the importance of feature normalization in the paper. Most importantly, our experiments on LFW BLUFR and MegaFace show that our additive margin softmax loss consistently performs better than the current state-of-the-art methods using the same network architecture and training dataset. Our code has also been made available at https://github.com/happynear/AMSoftmax

Additive Margin Softmax for Face Verification