{"url":"/method/mfr","slug":"mfr","name":"MFR","full_name":"Meta Face Recognition","full_name_withheld":false,"description_markdown":"**Meta Face Recognition** (MFR) is a meta-learning face recognition method. 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, domain-shift batches are built through a domain-level sampling strategy and back-propagated gradients/meta-gradients are obtained 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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Learning Meta Face Recognition in Unseen Domains","paper":"/paper/learning-meta-face-recognition-in-unseen","first_author":"Jianzhu Guo","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/learning-meta-face-recognition-in-unseen"},"source":{"url":"https://arxiv.org/abs/2003.07733v2","title":"Learning Meta Face Recognition in Unseen Domains","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Face Recognition Models","url":"/methods/category/face-recognition-models","pwc_aliases":[]}],"n_papers_tagged":19,"archive_num_papers":19,"papers_newest_first":[{"paper":"/paper/syzygy-of-thoughts-improving-llm-cot-with-the","title":"Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution","date":"2025-04-13","arxiv_id":"2504.09566","n_code_links":1,"syntology":null},{"paper":null,"title":"ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data","date":"2024-08-28","arxiv_id":"2408.16028","n_code_links":0,"syntology":null},{"paper":"/paper/epl-empirical-prototype-learning-for-deep","title":"EPL: Empirical Prototype Learning for Deep Face Recognition","date":"2024-05-21","arxiv_id":"2405.12447","n_code_links":1,"syntology":null},{"paper":null,"title":"A Comprehensive Survey of Masked Faces: Recognition, Detection, and Unmasking","date":"2024-05-09","arxiv_id":"2405.05900","n_code_links":0,"syntology":null},{"paper":"/paper/towards-progressive-multi-frequency","title":"Towards Progressive Multi-Frequency Representation for Image Warping","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/masked-face-dataset-generation-and-masked","title":"Masked Face Dataset Generation and Masked Face Recognition","date":"2023-11-13","arxiv_id":"2311.07475","n_code_links":3,"syntology":null},{"paper":null,"title":"Towards Large-scale Masked Face Recognition","date":"2023-10-25","arxiv_id":"2310.16364","n_code_links":0,"syntology":null},{"paper":"/paper/unitsface-unified-threshold-integrated-sample","title":"UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Localization using Multi-Focal Spatial Attention for Masked Face Recognition","date":"2023-05-03","arxiv_id":"2305.01905","n_code_links":0,"syntology":null},{"paper":null,"title":"Bayesian Non-parametric Hidden Markov Model for Agile Radar Pulse Sequences Streaming Analysis","date":"2023-02-09","arxiv_id":"2302.04407","n_code_links":0,"syntology":null},{"paper":"/paper/uniface-unified-cross-entropy-loss-for-deep","title":"UniFace: Unified Cross-Entropy Loss for Deep Face Recognition","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/masked-face-recognition-challenge-the-1","title":"Masked Face Recognition Challenge: The InsightFace Track Report","date":"2021-08-18","arxiv_id":"2108.08191","n_code_links":1,"syntology":null},{"paper":null,"title":"Masked Face Recognition Challenge: The WebFace260M Track Report","date":"2021-08-16","arxiv_id":"2108.07189","n_code_links":0,"syntology":null},{"paper":null,"title":"My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition","date":"2021-08-02","arxiv_id":"2108.00996","n_code_links":0,"syntology":null},{"paper":null,"title":"Visual Modulation of Human Responses to Support Surface Translation","date":"2021-03-05","arxiv_id":"2103.03722","n_code_links":0,"syntology":null},{"paper":null,"title":"Optical Flow Estimation via Motion Feature Recovery","date":"2021-01-16","arxiv_id":"2101.06333","n_code_links":0,"syntology":null},{"paper":null,"title":"Globally Optimal and Efficient Manhattan Frame Estimation by Delimiting Rotation Search Space","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Kernel based Matched Filter Approach for Segmentation of Retinal Blood Vessels","date":"2020-12-07","arxiv_id":"2012.03601","n_code_links":0,"syntology":null},{"paper":"/paper/learning-meta-face-recognition-in-unseen","title":"Learning Meta Face Recognition in Unseen Domains","date":"2020-03-17","arxiv_id":"2003.07733","n_code_links":8,"syntology":null}],"papers_shown":19,"tasks":[{"task":"/task/face-recognition","name":"Face Recognition","papers":10},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/bayesian-inference","name":"Bayesian Inference","papers":1},{"task":"/task/change-detection","name":"Change Detection","papers":1},{"task":"/task/change-point-detection","name":"Change Point Detection","papers":1},{"task":"/task/code-generation","name":"Code Generation","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/dataset-generation","name":"Dataset Generation","papers":1},{"task":"/task/gsm8k","name":"GSM8K","papers":1},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":1},{"task":"/task/math","name":"Math","papers":1},{"task":"/task/meta-learning","name":"Meta-Learning","papers":1},{"task":"/task/missing-values","name":"Missing Values","papers":1},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":1},{"task":null,"name":"Position","papers":1},{"task":"/task/scheduling","name":"Scheduling","papers":1},{"task":"/task/specificity","name":"Specificity","papers":1},{"task":"/task/super-resolution","name":"Super-Resolution","papers":1},{"task":"/task/survey","name":"Survey","papers":1}],"tasks_shown":20,"n_tasks":25,"usage_by_year":[{"year":"2020","papers":2},{"year":"2021","papers":6},{"year":"2023","papers":6},{"year":"2024","papers":4},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mfr"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}