Multi-Target Cross-Dataset Palmprint Recognition via Distilling From Multi-Teacher
Huikai Shao, Dexing Zhong · IEEE Transactions on Instrumentation and Measurement · 2023
Cross-dataset palmprint recognition is an important and popular topic, which has attracted more and more attention. In previous study, researchers are mainly focused on the scenarios of single-target or multi-source cross-dataset recognition. However, in practical application, the query images may be collected from multiple devices and environment, called multi-target cross-dataset palmprint recognition, which is much more challenging. In this paper, an approach is presented for multi-target cross-dataset palmprint recognition using knowledge distillation and domain adaptation, named Distilling From Multi-Teachers (DFMT). The source dataset is firstly paired with each of the multiple target datasets. Then, a teacher feature extractor is constructed to extract the adaptive knowledge of each pair using domain adaptation. Then, a student feature extractor is established to learn the adaptive knowledge from teacher feature extractors. Particularly, multi-level distillation losses are constructed to help to transfer the adaptive knowledge more effectively. Experiments are carried out on multiple palmprint databases such as contact database, contact-less database, constrained database, and unconstrained database. Experimental results demonstrate the superiority of DFMT compared to other competitive algorithms.