# FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization

arXiv: https://arxiv.org/abs/1911.11680 · HTML: https://mlsanity.com/paper/1911.11680/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 20 of 20)

- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [KeyPoint Relative Position Encoding for Face Recognition](https://mlsanity.com/paper/2403.14852/) (2024)
- [FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude](https://mlsanity.com/paper/2306.17206/) (2023)
- [Towards Realistic Generative 3D Face Models](https://mlsanity.com/paper/2304.12483/) (2023)
- [Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation](https://mlsanity.com/paper/2304.10066/) (2023)
- [SapiensID: Foundation for Human Recognition](https://mlsanity.com/paper/2504.04708/) (2025)
- [Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait](https://mlsanity.com/paper/2505.04616/) (2025)
- [FaceShield: Defending Facial Image against Deepfake Threats](https://mlsanity.com/paper/2412.09921/) (2024)
- [PETALface: Parameter Efficient Transfer Learning for Low-resolution Face Recognition](https://mlsanity.com/paper/2412.07771/) (2024)
- [NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition](https://mlsanity.com/paper/2103.03503/) (2021)
- [CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition](https://mlsanity.com/paper/2401.03037/) (2024)
- [Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition](https://mlsanity.com/paper/2211.15225/) (2022)
- [Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation](https://mlsanity.com/paper/2303.08665/) (2023)
- [Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation](https://mlsanity.com/paper/2308.06866/) (2023)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation](https://mlsanity.com/paper/2403.00561/) (2024)
- [Text-Guided Face Recognition using Multi-Granularity Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2312.09367/) (2023)
- [QGFace: Quality-Guided Joint Training For Mixed-Quality Face Recognition](https://mlsanity.com/paper/2312.17494/) (2023)
- [Learning Unified Representations for Multi-Resolution Face Recognition](https://mlsanity.com/paper/2310.09563/) (2023)
- [FaceMoE: Mixture of Experts for Low-Resolution Face Recognition](https://mlsanity.com/paper/2606.32040/) (2026)
- [Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints](https://mlsanity.com/paper/2609.01014/) (2026)

## Abstract (arXiv)

This paper studies face recognition (FR) and normalization in surveillance imagery. Surveillance FR is a challenging problem that has great values in law enforcement. Despite recent progress in conventional FR, less effort has been devoted to surveillance FR. To bridge this gap, we propose a Feature Adaptation Network (FAN) to jointly perform surveillance FR and normalization. Our face normalization mainly acts on the aspect of image resolution, closely related to face super-resolution. However, previous face super-resolution methods require paired training data with pixel-to-pixel correspondence, which is typically unavailable between real-world low-resolution and high-resolution faces. FAN can leverage both paired and unpaired data as we disentangle the features into identity and non-identity components and adapt the distribution of the identity features, which breaks the limit of current face super-resolution methods. We further propose a random scale augmentation scheme to learn resolution robust identity features, with advantages over previous fixed scale augmentation. Extensive experiments on LFW, WIDER FACE, QUML-SurvFace and SCface datasets have shown the effectiveness of our method on surveillance FR and normalization.