【论文整理】DNN-Face-Recognition-Papers Feature Normalization/Loss Function Method

Feature Normalization/Loss Function Method

• Large-Margin Softmax Loss for Convolutional Neural Networks(L-Softmax loss) [Weiyang Liu al., 2017] code

• SphereFace: Deep Hypersphere Embedding for Face Recognition(A-Softmax loss) [Weiyang Liu al., 2017]

• L2-constrained Softmax Loss for Discriminative Face Verification [Rajeev Ranjan al., 2017]

• Rethinking Feature Discrimination and Polymerization for Large-scale Recognition(CoCo loss) [Yu Liu al., 2017]

• NormFace: L2 Hypersphere Embedding for Face Verification [Feng Wang al., 2017]

• ArcFace: Additive Angular Margin Loss for Deep Face Recognition [Jiankang Deng al., 2018]

• DeepVisage: Making face recognition simple yet with powerful generalization skills [Abul Hasnat al., 2017]