# Adversarial Discriminative Heterogeneous Face Recognition

arXiv: https://arxiv.org/abs/1709.03675 · HTML: https://mlsanity.com/paper/1709.03675/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2017.

## Built on by (most cited first, 11 of 11)

- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [A Comprehensive Review of Deep Learning-based Single Image Super-resolution](https://mlsanity.com/paper/2102.09351/) (2021)
- [Towards NIR-VIS Masked Face Recognition](https://mlsanity.com/paper/2104.06761/) (2021)
- [Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement](https://mlsanity.com/paper/2206.04854/) (2022)
- [DAIL: Dataset-Aware and Invariant Learning for Face Recognition](https://mlsanity.com/paper/2101.05419/) (2021)
- [Physically-Based Face Rendering for NIR-VIS Face Recognition](https://mlsanity.com/paper/2211.06408/) (2022)
- [Template-based Multi-Domain Face Recognition](https://mlsanity.com/paper/2409.09832/) (2024)
- [Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition](https://mlsanity.com/paper/2204.11434/) (2022)
- [A NIR-to-VIS face recognition via part adaptive and relation attention module](https://mlsanity.com/paper/2102.00689/) (2021)
- [A Bidirectional Conversion Network for Cross-Spectral Face Recognition](https://mlsanity.com/paper/2205.01595/) (2022)
- [NIR-to-VIS Face Recognition via Embedding Relations and Coordinates of the Pairwise Features](https://mlsanity.com/paper/2208.02417/) (2022)

## Abstract (arXiv)

The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR). This paper proposes an adversarial discriminative feature learning framework to close the sensing gap via adversarial learning on both raw-pixel space and compact feature space. This framework integrates cross-spectral face hallucination and discriminative feature learning into an end-to-end adversarial network. In the pixel space, we make use of generative adversarial networks to perform cross-spectral face hallucination. An elaborate two-path model is introduced to alleviate the lack of paired images, which gives consideration to both global structures and local textures. In the feature space, an adversarial loss and a high-order variance discrepancy loss are employed to measure the global and local discrepancy between two heterogeneous distributions respectively. These two losses enhance domain-invariant feature learning and modality independent noise removing. Experimental results on three NIR-VIS databases show that our proposed approach outperforms state-of-the-art HFR methods, without requiring of complex network or large-scale training dataset.