StarLKNet: Star Mixup with Large Kernel Networks for Palm Vein Identification
This work addresses the need for more robust and accurate palm vein identification systems, which are important for biometric security applications, though it appears incremental by applying large kernel CNNs and Mixup to a specific domain.
The authors tackled the problem of limited effective receptive fields and insufficient training samples in palm vein identification by proposing StarLKNet, which combines a large kernel network (LaKNet) with a Mixup-based augmentation method (StarMix). The results showed that StarLKNet achieved the highest identification accuracy and lowest error on two public datasets, with StarMix providing superior augmentation and LaKNet offering stable performance gains.
As a representative of a new generation of biometrics, vein identification technology offers a high level of security and convenience.Convolutional neural networks (CNNs), a prominent class of deep learning architectures, have been extensively utilized for vein identification. Since their performance and robustness are limited by small \emph{Effective Receptive Fields} (\emph{e.g.}, 3$\times$3 kernels) and insufficient training samples, however, they are unable to extract global feature representations from vein images effectively. To address these issues, we propose \textbf{StarLKNet}, a large kernel convolution-based palm-vein identification network, with the Mixup approach.Our StarMix learns effectively the distribution of vein features to expand samples. To enable CNNs to capture comprehensive feature representations from palm-vein images, we explored the effect of convolutional kernel size on the performance of palm-vein identification networks and designed LaKNet, a network leveraging large kernel convolution and gating mechanism. In light of the current state of knowledge, this represents an inaugural instance of the deployment of a CNN with large kernels in the domain of vein identification. Extensive experiments were conducted to validate the performance of StarLKNet on two public palm-vein datasets. The results demonstrated that \textbf{StarMix} provided superior augmentation, and \textbf{LakNet} exhibited more stable performance gains compared to mainstream approaches, resulting in the highest identification accuracy and lowest identification error.