# Towards Universal Representation Learning for Deep Face Recognition

arXiv: https://arxiv.org/abs/2002.11841 · HTML: https://mlsanity.com/paper/2002.11841/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2020.

## Built on by (most cited first, 30 of 78)

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition](https://mlsanity.com/paper/2207.10299/) (2022)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [KeyPoint Relative Position Encoding for Face Recognition](https://mlsanity.com/paper/2403.14852/) (2024)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks](https://mlsanity.com/paper/2302.14685/) (2023)
- [A Quality Aware Sample-to-Sample Comparison for Face Recognition](https://mlsanity.com/paper/2306.04000/) (2023)
- [Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation](https://mlsanity.com/paper/2304.10066/) (2023)
- [50 Years of Automated Face Recognition](https://mlsanity.com/paper/2505.24247/) (2025)
- [LARNet: Lie Algebra Residual Network for Face Recognition](https://mlsanity.com/paper/2103.08147/) (2021)
- [Modality-Agnostic Debiasing for Single Domain Generalization](https://mlsanity.com/paper/2303.07123/) (2023)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [Cross-Domain Similarity Learning for Face Recognition in Unseen Domains](https://mlsanity.com/paper/2103.07503/) (2021)
- [TopoFR: A Closer Look at Topology Alignment on Face Recognition](https://mlsanity.com/paper/2410.10587/) (2024)
- [SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images](https://mlsanity.com/paper/2308.14570/) (2023)
- [BATT: Backdoor Attack with Transformation-based Triggers](https://mlsanity.com/paper/2211.01806/) (2022)
- [Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment](https://mlsanity.com/paper/2301.07845/) (2023)
- [Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning](https://mlsanity.com/paper/2504.07198/) (2025)
- [EQFace: A Simple Explicit Quality Network for Face Recognition](https://mlsanity.com/paper/2105.00634/) (2021)
- [TFS-ViT: Token-Level Feature Stylization for Domain Generalization](https://mlsanity.com/paper/2303.15698/) (2023)
- [PhysMLE: Generalizable and Priors-Inclusive Multi-task Remote Physiological Measurement](https://mlsanity.com/paper/2405.06201/) (2024)
- [Style Interleaved Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2207.03132/) (2022)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)
- [Harnessing Unrecognizable Faces for Improving Face Recognition](https://mlsanity.com/paper/2106.04112/) (2021)
- [Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation](https://mlsanity.com/paper/2203.14327/) (2022)
- [MorDeephy: Face Morphing Detection Via Fused Classification](https://mlsanity.com/paper/2208.03110/) (2022)
- [CoReFace: Sample-Guided Contrastive Regularization for Deep Face Recognition](https://mlsanity.com/paper/2304.11668/) (2023)

## Abstract (arXiv)

Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to adapt from the training data. Instead, we propose a universal representation learning framework that can deal with larger variation unseen in the given training data without leveraging target domain knowledge. We firstly synthesize training data alongside some semantically meaningful variations, such as low resolution, occlusion and head pose. However, directly feeding the augmented data for training will not converge well as the newly introduced samples are mostly hard examples. We propose to split the feature embedding into multiple sub-embeddings, and associate different confidence values for each sub-embedding to smooth the training procedure. The sub-embeddings are further decorrelated by regularizing variation classification loss and variation adversarial loss on different partitions of them. Experiments show that our method achieves top performance on general face recognition datasets such as LFW and MegaFace, while significantly better on extreme benchmarks such as TinyFace and IJB-S.