论文信息 - Improving Classification Performance of Softmax Loss Function Based on Scalable Batch-Normalization

Improving Classification Performance of Softmax Loss Function Based on Scalable Batch-Normalization

This work can be widely used in all kinds of pattern recognition systems based on deep learning, such as face recognition, license plate recognition, and speech recognition, etc.

[1] Qiuyu Zhu,et al. A New Loss Function for CNN Classifier Based on Predefined Evenly-Distributed Class Centroids , 2019, IEEE Access.

[2] Jian Cheng,et al. Additive Margin Softmax for Face Verification , 2018, IEEE Signal Processing Letters.