# From Modalities to Styles: Rethinking the Domain Gap in Heterogeneous Face Recognition

arXiv: https://arxiv.org/abs/2404.14247 · HTML: https://mlsanity.com/paper/2404.14247/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 66 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 16 of 16)

- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis](https://mlsanity.com/paper/1701.02096/) (2017)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition](https://mlsanity.com/paper/2103.16019/) (2021)
- [Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition](https://mlsanity.com/paper/1708.02412/) (2017)
- [DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition](https://mlsanity.com/paper/2009.09399/) (2020)
- [Dual Variational Generation for Low-Shot Heterogeneous Face Recognition](https://mlsanity.com/paper/1903.10203/) (2019)
- [Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-spectral Hallucination and Low-rank Embedding](https://mlsanity.com/paper/1611.06638/) (2016)
- [Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and Whistles](https://mlsanity.com/paper/2210.06529/) (2022)
- [Disentangled Variational Representation for Heterogeneous Face Recognition](https://mlsanity.com/paper/1809.01936/) (2018)
- [Generative Adversarial Network-based Synthesis of Visible Faces from Polarimetric Thermal Faces](https://mlsanity.com/paper/1708.02681/) (2017)
- [A Comprehensive Evaluation on Multi-channel Biometric Face Presentation Attack Detection](https://mlsanity.com/paper/2202.10286/) (2022)
- [Bridging the Gap: Heterogeneous Face Recognition with Conditional Adaptive Instance Modulation](https://mlsanity.com/paper/2307.07032/) (2023)

## Built on by (most cited first, 3 of 3)

- [xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devices](https://mlsanity.com/paper/2504.19646/) (2025)
- [Modality Agnostic Heterogeneous Face Recognition with Switch Style Modulators](https://mlsanity.com/paper/2407.08640/) (2024)
- [Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation](https://mlsanity.com/paper/2605.04769/) (2026)

## Abstract (arXiv)

Heterogeneous Face Recognition (HFR) focuses on matching faces from different domains, for instance, thermal to visible images, making Face Recognition (FR) systems more versatile for challenging scenarios. However, the domain gap between these domains and the limited large-scale datasets in the target HFR modalities make it challenging to develop robust HFR models from scratch. In our work, we view different modalities as distinct styles and propose a method to modulate feature maps of the target modality to address the domain gap. We present a new Conditional Adaptive Instance Modulation (CAIM ) module that seamlessly fits into existing FR networks, turning them into HFR-ready systems. The CAIM block modulates intermediate feature maps, efficiently adapting to the style of the source modality and bridging the domain gap. Our method enables end-to-end training using a small set of paired samples. We extensively evaluate the proposed approach on various challenging HFR benchmarks, showing that it outperforms state-of-the-art methods. The source code and protocols for reproducing the findings will be made publicly available