# A NIR-to-VIS face recognition via part adaptive and relation attention module

arXiv: https://arxiv.org/abs/2102.00689 · HTML: https://mlsanity.com/paper/2102.00689/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 13 of 13)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [L2-constrained Softmax Loss for Discriminative Face Verification](https://mlsanity.com/paper/1703.09507/) (2017)
- [Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition](https://mlsanity.com/paper/1708.02412/) (2017)
- [Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-spectral Hallucination and Low-rank Embedding](https://mlsanity.com/paper/1611.06638/) (2016)
- [Adversarial Discriminative Heterogeneous Face Recognition](https://mlsanity.com/paper/1709.03675/) (2017)
- [Coupled Deep Learning for Heterogeneous Face Recognition](https://mlsanity.com/paper/1704.02450/) (2017)
- [One-to-many face recognition with bilinear CNNs](https://mlsanity.com/paper/1506.01342/) (2015)
- [Relational Deep Feature Learning for Heterogeneous Face Recognition](https://mlsanity.com/paper/2003.00697/) (2020)

## Built on by (most cited first, 1 of 1)

- [Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition](https://mlsanity.com/paper/2204.11434/) (2022)

## Abstract (arXiv)

In the face recognition application scenario, we need to process facial images captured in various conditions, such as at night by near-infrared (NIR) surveillance cameras. The illumination difference between NIR and visible-light (VIS) causes a domain gap between facial images, and the variations in pose and emotion also make facial matching more difficult. Heterogeneous face recognition (HFR) has difficulties in domain discrepancy, and many studies have focused on extracting domain-invariant features, such as facial part relational information. However, when pose variation occurs, the facial component position changes, and a different part relation is extracted. In this paper, we propose a part relation attention module that crops facial parts obtained through a semantic mask and performs relational modeling using each of these representative features. Furthermore, we suggest component adaptive triplet loss function using adaptive weights for each part to reduce the intra-class identity regardless of the domain as well as pose. Finally, our method exhibits a performance improvement in the CASIA NIR-VIS 2.0 and achieves superior result in the BUAA-VisNir with large pose and emotion variations.