Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study
arxiv(2024)
摘要
Our study provides evidence that CNNs struggle to effectively extract
orientation features. We show that the use of Complex Structure Tensor, which
contains compact orientation features with certainties, as input to CNNs
consistently improves identification accuracy compared to using grayscale
inputs alone. Experiments also demonstrated that our inputs, which were
provided by mini complex conv-nets, combined with reduced CNN sizes,
outperformed full-fledged, prevailing CNN architectures. This suggests that the
upfront use of orientation features in CNNs, a strategy seen in mammalian
vision, not only mitigates their limitations but also enhances their
explainability and relevance to thin-clients. Experiments were done on publicly
available data sets comprising periocular images for biometric identification
and verification (Close and Open World) using 6 State of the Art CNN
architectures. We reduced SOA Equal Error Rate (EER) on the PolyU dataset by
5-26
更多查看译文
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