Computer Vision, Deep Learning

Liu, P., Liu, X., Yan, J., & Shao, J. (2018). Localization Guided Learning for Pedestrian Attribute Recognition. arXiv preprint arXiv:1808.09102.

Deng, J., Guo, J., & Zafeiriou, S. (2018). Arcface: Additive angular margin loss for deep face recognition. arXiv preprint arXiv:1801.07698.

Wang, F., Xiang, X., Cheng, J., & Yuille, A. L. (2017, October). Normface: l 2 hypersphere embedding for face verification. In Proceedings of the 2017 ACM on Multimedia Conference (pp. 1041-1049). ACM.

NormFace 主要从理论分析层面理解人脸识别中归一化 (Normalization) 问题。文献提出了两种策略是：

• 修改 softmax loss， 使用 cosine 相似度替代内积
• 引入每一类的 agent vector 改写度量学习