# Learning Meta Face Recognition in Unseen Domains

arXiv: https://arxiv.org/abs/2003.07733 · HTML: https://mlsanity.com/paper/2003.07733/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 30 of 61)

- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding](https://mlsanity.com/paper/2204.08129/) (2022)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [The Dawn of Quantum Natural Language Processing](https://mlsanity.com/paper/2110.06510/) (2021)
- [Meta Balanced Network for Fair Face Recognition](https://mlsanity.com/paper/2205.06548/) (2022)
- [Voice-Face Homogeneity Tells Deepfake](https://mlsanity.com/paper/2203.02195/) (2022)
- [TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection](https://mlsanity.com/paper/2104.07419/) (2021)
- [Multi-Objective Meta Learning](https://mlsanity.com/paper/2102.07121/) (2021)
- [Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.04618/) (2021)
- [Self-Supervised Video Representation Learning with Meta-Contrastive Network](https://mlsanity.com/paper/2108.08426/) (2021)
- [MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition](https://mlsanity.com/paper/2104.01876/) (2021)
- [Meta Spatio-Temporal Debiasing for Video Scene Graph Generation](https://mlsanity.com/paper/2207.11441/) (2022)
- [Domain-General Crowd Counting in Unseen Scenarios](https://mlsanity.com/paper/2212.02573/) (2022)
- [Learning to Unlearn for Robust Machine Unlearning](https://mlsanity.com/paper/2407.10494/) (2024)
- [Meta Compositional Referring Expression Segmentation](https://mlsanity.com/paper/2304.04415/) (2023)
- [Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation](https://mlsanity.com/paper/2107.12087/) (2021)
- [FACE-AUDITOR: Data Auditing in Facial Recognition Systems](https://mlsanity.com/paper/2304.02782/) (2023)
- [Information-Theoretic Bias Reduction via Causal View of Spurious Correlation](https://mlsanity.com/paper/2201.03121/) (2022)
- [Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions](https://mlsanity.com/paper/2209.01501/) (2022)
- [Cross-Domain Similarity Learning for Face Recognition in Unseen Domains](https://mlsanity.com/paper/2103.07503/) (2021)
- [Searching for Alignment in Face Recognition](https://mlsanity.com/paper/2102.05447/) (2021)
- [Model Inversion Robustness: Can Transfer Learning Help?](https://mlsanity.com/paper/2405.05588/) (2024)
- [A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2201.09846/) (2022)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [On the Vulnerability of Skip Connections to Model Inversion Attacks](https://mlsanity.com/paper/2409.01696/) (2024)
- [Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation](https://mlsanity.com/paper/2203.14327/) (2022)
- [The art of defense: letting networks fool the attacker](https://mlsanity.com/paper/2104.02963/) (2021)

## Abstract (arXiv)

Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization. For example, a well-trained model on webface data cannot deal with the ID vs. Spot task in surveillance scenario. In this paper, we aim to learn a generalized model that can directly handle new unseen domains without any model updating. To this end, we propose a novel face recognition method via meta-learning named Meta Face Recognition (MFR). MFR synthesizes the source/target domain shift with a meta-optimization objective, which requires the model to learn effective representations not only on synthesized source domains but also on synthesized target domains. Specifically, we build domain-shift batches through a domain-level sampling strategy and get back-propagated gradients/meta-gradients on synthesized source/target domains by optimizing multi-domain distributions. The gradients and meta-gradients are further combined to update the model to improve generalization. Besides, we propose two benchmarks for generalized face recognition evaluation. Experiments on our benchmarks validate the generalization of our method compared to several baselines and other state-of-the-arts. The proposed benchmarks will be available at https://github.com/cleardusk/MFR.