Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition
This addresses face recognition challenges in cross-domain scenarios like security and surveillance, but it is incremental as it builds on existing knowledge distillation and alignment techniques.
The paper tackles the problem of heterogeneous face recognition (HFR) across domains like NIR-VIS and VIS-VIS, where domain discrepancy and data scarcity degrade performance, by proposing joint feature distribution alignment learning (JFDAL) to achieve high HFR performance while retaining original VIS domain accuracy, with experiments showing statistically significant improvements over fine-tuning and comparable HFR performance to state-of-the-art methods on datasets like Oulu-CASIA NIR&VIS.
Face recognition for visible light (VIS) images achieve high accuracy thanks to the recent development of deep learning. However, heterogeneous face recognition (HFR), which is a face matching in different domains, is still a difficult task due to the domain discrepancy and lack of large HFR dataset. Several methods have attempted to reduce the domain discrepancy by means of fine-tuning, which causes significant degradation of the performance in the VIS domain because it loses the highly discriminative VIS representation. To overcome this problem, we propose joint feature distribution alignment learning (JFDAL) which is a joint learning approach utilizing knowledge distillation. It enables us to achieve high HFR performance with retaining the original performance for the VIS domain. Extensive experiments demonstrate that our proposed method delivers statistically significantly better performances compared with the conventional fine-tuning approach on a public HFR dataset Oulu-CASIA NIR&VIS and popular verification datasets in VIS domain such as FLW, CFP, AgeDB. Furthermore, comparative experiments with existing state-of-the-art HFR methods show that our method achieves a comparable HFR performance on the Oulu-CASIA NIR&VIS dataset with less degradation of VIS performance.