et al., CVPR 2019, https://arxiv.org/abs/1901.07590 [2] Focal Loss for Dense Object Detection, T. Lin et al., CVPR 2017, https://arxiv.org/abs/1708.02002 [3] Large-Margin Softmax Loss for Convolutional Neural Networks, W. Liu et al., ICML 2016, https://arxiv.org/abs/1612.02295 [4] SphereFace: Deep Hypersphere Embedding for Face Recognition, W. Liu et al., CVPR 2017, https://arxiv.org/abs/1704.08063 [5] CosFace: Large Margin Cosine Loss for Deep Face Recognition, H. Wang et al., CVPR 2018, https://arxiv.org/abs/1801.09414 [6] Additive Margin Softmax for Face Verification, F. Wang et al., Signal Processing Letters 2018, https://arxiv.org/abs/1801.05599 [7] ArcFace: Additive Angular Margin Loss for Deep Face Recognition, J. Deng et al., CVPR 2019, https://arxiv.org/abs/1801.07698 [8] Class-Balanced Loss Based on Effective Number of Samples, Y. Cui et al., CVPR 2019, https://arxiv.org/abs/1901.05555 [9] AdaptiveFace: Adaptive Margin and Sampling for Face Recognition, H. Liu et al., CVPR 2019 [10] UniformFace: Learning Deep Equidistributed Representation for Face Recognition, Y. Duana et al., CVPR 2019 [11] Unequal-training for Deep Face Recognition with Long-tailed Noisy Data, Y. Zhong et al., CVPR 2019 [12] Dropout as a bayesian approximation: Representing model uncertainty in deep learning, Y. Gal and Z. Ghahramani, ICML 2016, https://arxiv.org/abs/1506.02142 [13] Max-margin Class Imbalanced Learning with Gaussian Affinity, M. Hayat et al., https://arxiv.org/abs/1901.07711