Heterogeneous Face Recognition Using Domain Invariant Units

TL;DR

This paper introduces Domain-Invariant Units (DIU), a novel method leveraging a pretrained face recognition model to improve heterogeneous face recognition across different modalities with limited data, showing superior benchmark performance.

Contribution

The paper proposes a new domain-invariant layer learning approach using contrastive distillation, enhancing pretrained models for heterogeneous face recognition tasks.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effective with limited paired training data.

Reduces domain gap between different face image modalities.

Abstract

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.