Discriminative metric learning for face verification using enhanced Siamese neural network
MULTIMEDIA TOOLS AND APPLICATIONS(2020)
摘要
Although face verification algorithms have made great success under controlled conditions in recent years, there’s plenty of room at its performance under uncontrolled real-world due to lack of discriminative feature representation ability. From the perspective of metric learning, we proposed a context-aware based Siamese neural network (CASNN) to learn a simple yet powerful network for face verification task to enhance its discriminative feature representation ability. Firstly, a context-aware module is used to automatically focus on the key area of the input facial images without irrelevant background area. Then we design a Siamese network equipped with center-classification loss to compress intra-class features and enlarge between-class ones for discriminative metric learning. Finally, we propose a quantitative indicator named “D-score” to show the discriminative representation ability of the learnt features from different methods. The extensive experiments are conducted on LFW dataset, YouTube Face dataset (YTF) and real-world dataset. The results confirm that CASNN outperforms some state-of-the-art deep learning-based face verification methods.
更多查看译文
关键词
Metric learning,Discriminative feature,Siamese neural network,Face verification
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要