Knot Magnify Loss for Face Recognition

  title={Knot Magnify Loss for Face Recognition},
  author={Qiang Rao and Ting Yu and Yun Yang and Bailan Feng},
  journal={2018 25th IEEE International Conference on Image Processing (ICIP)},
  • Qiang Rao, Ting Yu, +1 author Bailan Feng
  • Published 2018
  • Computer Science
  • 2018 25th IEEE International Conference on Image Processing (ICIP)
Deep Convolutional Neural Netowrks (DCNN) have significantly improved the performance of face recognition in recent years. Softmax loss is the most widely used loss function for training the DCNN-based face recognition system. It gives the same weights to easy and hard samples in one batch, which would leads to performance gap on the quality imbalanced data. In this paper, we discover that the rare hard samples in the training dataset has become a main obstacle for training a robust face… Expand
Regularization and Iterative Initialization of Softmax for Fast Training of Convolutional Neural Networks


L2-constrained Softmax Loss for Discriminative Face Verification
A Discriminative Feature Learning Approach for Deep Face Recognition
Web-scale training for face identification
SphereFace: Deep Hypersphere Embedding for Face Recognition
Learning Face Representation from Scratch
Deeply learned face representations are sparse, selective, and robust
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
FaceNet: A unified embedding for face recognition and clustering
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Deep Face Recognition