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 FSF_{S} and FTF_{T} . Firstly, FSF_{S} is trained as a teacher using labeled source samples to help learn FTF_{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, FTF_{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.

中文翻译：

---

与合作伙伴学习提升多源跨数据集掌纹识别


受益于安全可靠的优势，基于深度学习的掌纹识别受到了广泛关注。然而，以前的方法主要集中在单个数据集中的掌纹识别。在一些实际应用中，可能可以获得在不同条件下从多个设备收集的一定数量的掌纹图像。由于不同数据集之间存在差距，如何有效地使用它们以获得满意的性能是一个重要且具有挑战性的问题。在本文中，我们提出了一种新颖的与合作伙伴学习（LWP）框架来改进多源跨数据集掌纹识别。选择多个标记的源数据集和一个未标记的数据集作为伙伴来训练两个特征提取器 FSF_{S} 和 FTF_{T} 。首先，使用标记的源样本将 FSF_{S} 训练为教师，以帮助学习 FTF_{T} 。然后，引入适应损失来限制源数据集和目标数据集之间的差异。为了减轻未标记目标样本对模型的负面影响，进一步提出了包括两个距离损失的一致性损失，以及时纠正误导。最后，FTF_{T} 可以提取自适应特征以将目标与源进行匹配。在几个基准掌纹数据库上进行了大量的实验，结果表明我们提出的 LWP 可以大幅优于其他比较基线。这些代码可在 http://gr.xjtu.edu.cn/web/bell 上公开获取。