Bridging the Gap: Heterogeneous Face Recognition with Conditional Adaptive Instance Modulation

TL;DR

This paper introduces a novel Conditional Adaptive Instance Modulation (CAIM) module that adapts pre-trained face recognition networks for heterogeneous face recognition tasks, effectively bridging domain gaps such as thermal and visible spectra.

Contribution

The work proposes a new CAIM module that can be integrated into existing networks to enable effective HFR with minimal paired data, improving cross-domain face matching.

Findings

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

Enables end-to-end training with limited paired samples.

Successfully bridges domain gaps between different face modalities.

Abstract

Heterogeneous Face Recognition (HFR) aims to match face images across different domains, such as thermal and visible spectra, expanding the applicability of Face Recognition (FR) systems to challenging scenarios. However, the domain gap and limited availability of large-scale datasets in the target domain make training robust and invariant HFR models from scratch difficult. In this work, we treat different modalities as distinct styles and propose a framework to adapt feature maps, bridging the domain gap. We introduce a novel Conditional Adaptive Instance Modulation (CAIM) module that can be integrated into pre-trained FR networks, transforming them into HFR networks. The CAIM block modulates intermediate feature maps, to adapt the style of the target modality effectively bridging the domain gap. Our proposed method allows for end-to-end training with a minimal number of paired samples. We extensively evaluate our approach on multiple challenging benchmarks, demonstrating superior performance compared to state-of-the-art methods. The source code and protocols for reproducing the findings will be made publicly available.