Learning with Partners to Improve the Multi-Source Cross-Dataset Palmprint Recognition

Benefiting from the advantages of safety and reliability, deep learning-based palmprint recognition has attracted widespread attention. However, previous methods are mainly focused on palmprint recognition in a single dataset. In some realistic applications, a certain number of palmprint images collected from multiple devices under different conditions may be available. Due to the existing gaps between different datasets, how to efficiently use them to obtain satisfactory performance is an important and challenging issue. In this paper, we propose a novel Learning with Partners (LWP) framework to improve the multi-source cross-dataset palmprint recognition. Multiple labeled source datasets and an unlabeled dataset are selected as partners to train two feature extractors $F_{S}$ and $F_{T}$. Firstly, $F_{S}$ is trained as a teacher using labeled source samples to help learn $F_{T}$. Then, adaptation loss is introduced to constrain the discrepancy between source and target datasets. To alleviate the negative impact of unlabeled target samples on the model, consistency loss including two distance losses are further proposed to correct the misleading in time. Finally, $F_{T}$ can extract adaptive features to match the target with sources. Extensive experiments are conducted on several benchmark palmprint databases and the results demonstrate that our proposed LWP can outperform other comparative baselines by a large margin. The codes are publicly available at http://gr.xjtu.edu.cn/web/bell.