GTC Silicon Valley-2019 ID:S9631:Deep Hyperspherical Embedding and Decoupled Learning for Visual Recognition
Weiyang Liu(Georgia Institute of Technology),Zhen Liu(Georgia Institute of Technology)
We'll introduce several deep angular/hyperpherical learning frameworks and their applications in computer vision. Deep angular/hyperspherical learning provides state-of-the-art performance for general image classification and face recognition problems. We'll talk about the motivation behind this type of learning and introduce some relevant variants under this framework. Deep hyperspherical learning has diverse applications in computer vision, and can also be used for learning neural network architectures and improving neural network generalization. We'll also discuss a few open problems in this framework and talk about some potential applications.