Heterogeneous Face Recognition Using Domain Invariant Units
This work addresses the challenge of matching face images across different domains, which is incremental as it builds on pretrained models to enhance adaptability.
The paper tackles the problem of Heterogeneous Face Recognition (HFR) by reducing the domain gap between modalities like thermal and visible spectra, using Domain-Invariant Units (DIU) trained with contrastive distillation, and demonstrates superior performance on multiple benchmarks.
Heterogeneous Face Recognition (HFR) aims to expand the applicability of Face Recognition (FR) systems to challenging scenarios, enabling the matching of face images across different domains, such as matching thermal images to visible spectra. However, the development of HFR systems is challenging because of the significant domain gap between modalities and the lack of availability of large-scale paired multi-channel data. In this work, we leverage a pretrained face recognition model as a teacher network to learn domaininvariant network layers called Domain-Invariant Units (DIU) to reduce the domain gap. The proposed DIU can be trained effectively even with a limited amount of paired training data, in a contrastive distillation framework. This proposed approach has the potential to enhance pretrained models, making them more adaptable to a wider range of variations in data. We extensively evaluate our approach on multiple challenging benchmarks, demonstrating superior performance compared to state-of-the-art methods.