InterFace:Adjustable Angular Margin Inter-class Loss for Deep Face Recognition. (arXiv:2210.02018v1 [cs.CV])

In the field of face recognition, it is always a hot research topic to
improve the loss solution to make the face features extracted by the network
have greater discriminative power. Research works in recent years has improved
the discriminative power of the face model by normalizing softmax to the cosine
space step by step and then adding a fixed penalty margin to reduce the
intra-class distance to increase the inter-class distance. Although a great
deal of previous work has …

angular arxiv face face recognition loss