{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/arcface","slug":"arcface","name":"ArcFace","full_name":"Additive Angular Margin Loss","full_name_withheld":false,"description_markdown":"**ArcFace**, or **Additive Angular Margin Loss**, is a loss function used in face recognition tasks. The [softmax](https://paperswithcode.com/method/softmax) is traditionally used in these tasks. However, the softmax loss function does not explicitly optimise the feature embedding to enforce higher similarity for intraclass samples and diversity for inter-class samples, which results in a performance gap for deep face recognition under large intra-class appearance variations. \r\n\r\nThe ArcFace loss transforms the logits $W^{T}\\_{j}x\\_{i} = || W\\_{j} || \\text{ } || x\\_{i} || \\cos\\theta\\_{j}$,\r\nwhere $\\theta\\_{j}$ is the angle between the weight $W\\_{j}$ and the feature $x\\_{i}$. The individual weight $ || W\\_{j} || = 1$ is fixed by $l\\_{2}$ normalization. The embedding feature $ ||x\\_{i} ||$ is fixed by $l\\_{2}$ normalization and re-scaled to $s$. The normalisation step on features and weights makes the predictions only depend on the angle between the feature and the weight. The learned embedding\r\nfeatures are thus distributed on a hypersphere with a radius of $s$. Finally, an additive angular margin penalty $m$ is added between $x\\_{i}$ and $W\\_{y\\_{i}}$ to simultaneously enhance the intra-class compactness and inter-class discrepancy. Since the proposed additive angular margin penalty is\r\nequal to the geodesic distance margin penalty in the normalised hypersphere, the method is named ArcFace:\r\n\r\n$$ L\\_{3} = -\\frac{1}{N}\\sum^{N}\\_{i=1}\\log\\frac{e^{s\\left(\\cos\\left(\\theta\\_{y\\_{i}} + m\\right)\\right)}}{e^{s\\left(\\cos\\left(\\theta\\_{y\\_{i}} + m\\right)\\right)} + \\sum^{n}\\_{j=1, j \\neq y\\_{i}}e^{s\\cos\\theta\\_{j}}} $$\r\n\r\nThe authors select face images from 8 different identities containing enough samples (around 1,500 images/class) to train 2-D feature embedding networks with the softmax and ArcFace loss, respectively. As the Figure shows, the softmax loss provides roughly separable feature embedding\r\nbut produces noticeable ambiguity in decision boundaries, while the proposed ArcFace loss can obviously enforce a more evident gap between the nearest classes.\r\n\r\nOther alternatives to enforce intra-class compactness and inter-class distance include [Supervised Contrastive Learning](https://arxiv.org/abs/2004.11362).","description_state":"present","introduced_year":null,"introduced_by":{"title":"ArcFace: Additive Angular Margin Loss for Deep Face Recognition","paper":"/paper/arcface-additive-angular-margin-loss-for-deep","first_author":"Jiankang Deng","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/arcface-additive-angular-margin-loss-for-deep"},"source":{"url":"https://arxiv.org/abs/1801.07698v4","title":"ArcFace: Additive Angular Margin Loss for Deep Face Recognition","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/ronghuaiyang/arcface-pytorch/blob/47ace80b128042cd8d2efd408f55c5a3e156b032/models/metrics.py#L10","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":94,"archive_num_papers":94,"papers_newest_first":[{"paper":null,"slug":"enhancing-few-shot-keyword-spotting","title":"Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models","date":"2025-06-21","arxiv_id":"2506.17686","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-large-scale-pose-invariant-face","title":"Towards Large-Scale Pose-Invariant Face Recognition Using Face Defrontalization","date":"2025-06-04","arxiv_id":"2506.04496","n_code_links":0,"syntology":null},{"paper":null,"slug":"accuracy-and-fairness-of-facial-recognition","title":"Accuracy and Fairness of Facial Recognition Technology in Low-Quality Police Images: An Experiment With Synthetic Faces","date":"2025-05-20","arxiv_id":"2505.14320","n_code_links":0,"syntology":null},{"paper":null,"slug":"lapig-cross-modal-generation-of-paired","title":"LaPIG: Cross-Modal Generation of Paired Thermal and Visible Facial Images","date":"2025-03-20","arxiv_id":"2503.16376","n_code_links":0,"syntology":null},{"paper":"/paper/universal-embedding-function-for-traffic","slug":"universal-embedding-function-for-traffic","title":"Universal Embedding Function for Traffic Classification via QUIC Domain Recognition Pretraining: A Transfer Learning Success","date":"2025-02-18","arxiv_id":"2502.12930","n_code_links":1,"syntology":null},{"paper":null,"slug":"omni-id-holistic-identity-representation","title":"Omni-ID: Holistic Identity Representation Designed for Generative Tasks","date":"2024-12-12","arxiv_id":"2412.09694","n_code_links":0,"syntology":null},{"paper":"/paper/multispecies-animal-re-id-using-a-large","slug":"multispecies-animal-re-id-using-a-large","title":"Multispecies Animal Re-ID Using a Large Community-Curated Dataset","date":"2024-12-07","arxiv_id":"2412.05602","n_code_links":1,"syntology":null},{"paper":null,"slug":"pairwise-discernment-of-affectnet-expressions","title":"Pairwise Discernment of AffectNet Expressions with ArcFace","date":"2024-12-01","arxiv_id":"2412.01860","n_code_links":0,"syntology":null},{"paper":null,"slug":"hypersphere-secure-sketch-revisited","title":"Hypersphere Secure Sketch Revisited: Probabilistic Linear Regression Attack on IronMask in Multiple Usage","date":"2024-09-19","arxiv_id":"2409.12884","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-02494","title":"HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions","date":"2024-08-05","arxiv_id":"2408.02494","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-the-feature-extractor-networks-for","slug":"analyzing-the-feature-extractor-networks-for","title":"Analyzing the Feature Extractor Networks for Face Image Synthesis","date":"2024-06-04","arxiv_id":"2406.02153","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-privacy-funnel-model-from-a","title":"Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition","date":"2024-04-03","arxiv_id":"2404.02696","n_code_links":0,"syntology":null},{"paper":"/paper/arc2face-a-foundation-model-of-human-faces","slug":"arc2face-a-foundation-model-of-human-faces","title":"Arc2Face: A Foundation Model for ID-Consistent Human Faces","date":"2024-03-18","arxiv_id":"2403.11641","n_code_links":3,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["huggingface.co/FoivosPar/Arc2Face"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/vigface-virtual-identity-generation-model-for","slug":"vigface-virtual-identity-generation-model-for","title":"VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition","date":"2024-03-13","arxiv_id":"2403.08277","n_code_links":1,"syntology":null},{"paper":null,"slug":"mitigating-the-impact-of-attribute-editing-on","title":"Mitigating the Impact of Attribute Editing on Face Recognition","date":"2024-03-12","arxiv_id":"2403.08092","n_code_links":0,"syntology":null},{"paper":null,"slug":"x2-softmax-margin-adaptive-loss-function-for","title":"X2-Softmax: Margin Adaptive Loss Function for Face Recognition","date":"2023-12-08","arxiv_id":"2312.05281","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-face-representation-via-joint-label","title":"Improved Face Representation via Joint Label Classification and Supervised Contrastive Clustering","date":"2023-12-07","arxiv_id":"2312.04029","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-universal-anti-spoofing-approach-for","title":"A Universal Anti-Spoofing Approach for Contactless Fingerprint Biometric Systems","date":"2023-10-23","arxiv_id":"2310.15044","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-simplicial","title":"An Empirical Study of Self-supervised Learning with Wasserstein Distance","date":"2023-10-16","arxiv_id":"2310.10143","n_code_links":0,"syntology":null},{"paper":null,"slug":"trading-off-mutual-information-on-feature","title":"Trading-off Mutual Information on Feature Aggregation for Face Recognition","date":"2023-09-22","arxiv_id":"2309.13137","n_code_links":0,"syntology":null},{"paper":"/paper/unitsface-unified-threshold-integrated-sample","slug":"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":"/paper/patent-image-retrieval-using-transformer","slug":"patent-image-retrieval-using-transformer","title":"Patent image retrieval using transformer-based deep metric learning","date":"2023-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/global-features-are-all-you-need-for-image","slug":"global-features-are-all-you-need-for-image","title":"Global Features are All You Need for Image Retrieval and Reranking","date":"2023-08-14","arxiv_id":"2308.06954","n_code_links":2,"syntology":{"ran":14,"of":18,"n_ran_checked":12,"n_instrument":2,"unverified":4,"pointer_only":0,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shihaoshao-gh/superglobal"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":9,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-face-recognition-from-caption","title":"Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation","date":"2023-08-13","arxiv_id":"2308.06866","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-biometric-capacity-of-generative-face","title":"On the Biometric Capacity of Generative Face Models","date":"2023-08-03","arxiv_id":"2308.02065","n_code_links":0,"syntology":null},{"paper":"/paper/promptstyler-prompt-driven-style-generation","slug":"promptstyler-prompt-driven-style-generation","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","date":"2023-07-27","arxiv_id":"2307.15199","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"rpg-palm-realistic-pseudo-data-generation-for","title":"RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition","date":"2023-07-26","arxiv_id":"2307.14016","n_code_links":0,"syntology":null},{"paper":null,"slug":"childgan-large-scale-synthetic-child-facial","title":"ChildGAN: Large Scale Synthetic Child Facial Data Using Domain Adaptation in StyleGAN","date":"2023-07-25","arxiv_id":"2307.13746","n_code_links":0,"syntology":null},{"paper":null,"slug":"imperceptible-physical-attack-against-face","title":"Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation","date":"2023-07-25","arxiv_id":"2307.13294","n_code_links":0,"syntology":null},{"paper":"/paper/blendface-re-designing-identity-encoders-for","slug":"blendface-re-designing-identity-encoders-for","title":"BlendFace: Re-designing Identity Encoders for Face-Swapping","date":"2023-07-20","arxiv_id":"2307.10854","n_code_links":2,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["mapooon/blendface"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/lightformer-an-end-to-end-model-for","slug":"lightformer-an-end-to-end-model-for","title":"LightFormer: An End-to-End Model for Intersection Right-of-Way Recognition Using Traffic Light Signals and an Attention Mechanism","date":"2023-07-14","arxiv_id":"2307.07196","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-selection-of-text-to-speech-data-to","title":"Towards Selection of Text-to-speech Data to Augment ASR Training","date":"2023-05-30","arxiv_id":"2306.00998","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-minimizing-efforts-for-morphing","title":"Towards minimizing efforts for Morphing Attacks -- Deep embeddings for morphing pair selection and improved Morphing Attack Detection","date":"2023-05-29","arxiv_id":"2305.18216","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-machine-comparison-for-cross-race-face","title":"Human-Machine Comparison for Cross-Race Face Verification: Race Bias at the Upper Limits of Performance?","date":"2023-05-25","arxiv_id":"2305.16443","n_code_links":0,"syntology":null},{"paper":"/paper/ghostfacenets-lightweight-face-recognition","slug":"ghostfacenets-lightweight-face-recognition","title":"GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations","date":"2023-04-10","arxiv_id":null,"n_code_links":7,"syntology":null},{"paper":"/paper/patent-image-retrieval-using-cross-entropy","slug":"patent-image-retrieval-using-cross-entropy","title":"Patent Image Retrieval Using Cross-entropy-based Metric Learning","date":"2023-02-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fra-a-novel-face-representation-augmentation","title":"Enhancing Face Recognition with Latent Space Data Augmentation and Facial Posture Reconstruction","date":"2023-01-27","arxiv_id":"2301.11986","n_code_links":0,"syntology":null},{"paper":"/paper/uniface-unified-cross-entropy-loss-for-deep","slug":"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/faceqan-face-image-quality-assessment-through","slug":"faceqan-face-image-quality-assessment-through","title":"FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration","date":"2022-12-05","arxiv_id":"2212.02127","n_code_links":1,"syntology":null},{"paper":null,"slug":"supervised-fine-tuning-evaluation-for-long","title":"Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition","date":"2022-11-14","arxiv_id":"2211.07696","n_code_links":0,"syntology":null},{"paper":"/paper/improving-deep-facial-phenotyping-for-ultra","slug":"improving-deep-facial-phenotyping-for-ultra","title":"Improving Deep Facial Phenotyping for Ultra-rare Disorder Verification Using Model Ensembles","date":"2022-11-12","arxiv_id":"2211.06764","n_code_links":1,"syntology":null},{"paper":"/paper/5th-place-solution-to-kaggle-google-universal","slug":"5th-place-solution-to-kaggle-google-universal","title":"5th Place Solution to Kaggle Google Universal Image Embedding Competition","date":"2022-10-18","arxiv_id":"2210.09495","n_code_links":1,"syntology":null},{"paper":null,"slug":"6th-place-solution-to-google-universal-image","title":"6th Place Solution to Google Universal Image Embedding","date":"2022-10-17","arxiv_id":"2210.09377","n_code_links":0,"syntology":null},{"paper":null,"slug":"3rd-place-solution-for-google-universal-image","title":"3rd Place Solution for Google Universal Image Embedding","date":"2022-10-14","arxiv_id":"2210.09296","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gan-induced-attribute-manipulations","title":"Can GAN-induced Attribute Manipulations Impact Face Recognition?","date":"2022-09-07","arxiv_id":"2209.02941","n_code_links":0,"syntology":null},{"paper":"/paper/duetface-collaborative-privacy-preserving","slug":"duetface-collaborative-privacy-preserving","title":"DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain","date":"2022-07-15","arxiv_id":"2207.07340","n_code_links":1,"syntology":null},{"paper":"/paper/continuous-facial-motion-deblurring","slug":"continuous-facial-motion-deblurring","title":"Continuous Facial Motion Deblurring","date":"2022-07-14","arxiv_id":"2207.06626","n_code_links":1,"syntology":null},{"paper":"/paper/are-gan-based-morphs-threatening-face","slug":"are-gan-based-morphs-threatening-face","title":"Are GAN-based Morphs Threatening Face Recognition?","date":"2022-05-05","arxiv_id":"2205.02496","n_code_links":1,"syntology":null},{"paper":null,"slug":"otface-hard-samples-guided-optimal-transport","title":"OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation","date":"2022-03-28","arxiv_id":"2203.14461","n_code_links":0,"syntology":null},{"paper":null,"slug":"geometric-synthesis-a-free-lunch-for-large","title":"Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining","date":"2022-03-11","arxiv_id":"2203.05703","n_code_links":0,"syntology":null},{"paper":"/paper/probabilistic-embeddings-revisited","slug":"probabilistic-embeddings-revisited","title":"Probabilistic Embeddings Revisited","date":"2022-02-14","arxiv_id":"2202.06768","n_code_links":1,"syntology":{"ran":8,"of":18,"n_ran_checked":8,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["tinkoff-ai/probabilistic-embeddings"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fun-selfie-filters-in-face-recognition-impact","title":"Fun Selfie Filters in Face Recognition: Impact Assessment and Removal","date":"2022-02-12","arxiv_id":"2202.06022","n_code_links":0,"syntology":null},{"paper":null,"slug":"arcface-knows-the-gender-too","title":"ArcFace Knows the Gender, Too!","date":"2021-12-19","arxiv_id":"2112.10101","n_code_links":0,"syntology":null},{"paper":null,"slug":"distill-and-de-bias-mitigating-bias-in-face","title":"Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation","date":"2021-12-17","arxiv_id":"2112.09786","n_code_links":0,"syntology":null},{"paper":"/paper/producing-augmentation-invariant-embeddings","slug":"producing-augmentation-invariant-embeddings","title":"Producing augmentation-invariant embeddings from real-life imagery","date":"2021-12-06","arxiv_id":"2112.03415","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["socom20/facebook-image-similarity-challenge-2021"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"longitudinal-analysis-of-mask-and-no-mask-on","title":"Longitudinal Analysis of Mask and No-Mask on Child Face Recognition","date":"2021-10-29","arxiv_id":"2111.00121","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-insight-into-measuring-face-image","title":"A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics","date":"2021-10-21","arxiv_id":"2110.11111","n_code_links":0,"syntology":null},{"paper":null,"slug":"google-landmark-retrieval-2021-competition","title":"Google Landmark Retrieval 2021 Competition Third Place Solution","date":"2021-10-09","arxiv_id":"2110.04619","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-large-scale-image-retrieval-with","slug":"efficient-large-scale-image-retrieval-with","title":"Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers","date":"2021-10-07","arxiv_id":"2110.03786","n_code_links":1,"syntology":null},{"paper":null,"slug":"3rd-place-solution-to-google-landmark-1","title":"3rd Place Solution to Google Landmark Recognition Competition 2021","date":"2021-10-06","arxiv_id":"2110.02794","n_code_links":0,"syntology":null},{"paper":null,"slug":"dodging-attack-using-carefully-crafted","title":"Dodging Attack Using Carefully Crafted Natural Makeup","date":"2021-09-14","arxiv_id":"2109.06467","n_code_links":0,"syntology":null},{"paper":null,"slug":"ossr-pid-one-shot-symbol-recognition-in-p-id","title":"OSSR-PID: One-Shot Symbol Recognition in P&ID Sheets using Path Sampling and GCN","date":"2021-09-08","arxiv_id":"2109.03849","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-relighting-against-face","title":"Adversarial Relighting Against Face Recognition","date":"2021-08-18","arxiv_id":"2108.07920","n_code_links":0,"syntology":null},{"paper":null,"slug":"demographic-fairness-in-face-identification","title":"Demographic Fairness in Face Identification: The Watchlist Imbalance Effect","date":"2021-06-15","arxiv_id":"2106.08049","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-masked-face-recognition-with-multi","title":"Boosting Masked Face Recognition with Multi-Task ArcFace","date":"2021-04-20","arxiv_id":"2104.09874","n_code_links":0,"syntology":null},{"paper":"/paper/facesec-a-fine-grained-robustness-evaluation","slug":"facesec-a-fine-grained-robustness-evaluation","title":"FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems","date":"2021-04-08","arxiv_id":"2104.04107","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["KnowledgeDiscovery/FaceSec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ironmask-modular-architecture-for-protecting","title":"IronMask: Modular Architecture for Protecting Deep Face Template","date":"2021-04-06","arxiv_id":"2104.02239","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-geometric-constraints-from","title":"Harnessing Geometric Constraints from Emotion Labels to improve Face Verification","date":"2021-03-05","arxiv_id":"2103.03862","n_code_links":0,"syntology":null},{"paper":"/paper/when-face-recognition-meets-occlusion-a-new","slug":"when-face-recognition-meets-occlusion-a-new","title":"When Face Recognition Meets Occlusion: A New Benchmark","date":"2021-03-04","arxiv_id":"2103.02805","n_code_links":1,"syntology":null},{"paper":"/paper/multiface-a-generic-training-mechanism-for","slug":"multiface-a-generic-training-mechanism-for","title":"MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance","date":"2021-01-25","arxiv_id":"2101.09899","n_code_links":1,"syntology":null},{"paper":null,"slug":"switchable-k-class-hyperplanes-for-noise","title":"Switchable K-Class Hyperplanes for Noise-Robust Representation Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/this-face-does-not-exist-but-it-might-be","slug":"this-face-does-not-exist-but-it-might-be","title":"This Face Does Not Exist ... But It Might Be Yours! Identity Leakage in Generative Models","date":"2020-12-10","arxiv_id":"2101.05084","n_code_links":1,"syntology":null},{"paper":"/paper/vulnerability-analysis-of-face-morphing","slug":"vulnerability-analysis-of-face-morphing","title":"Vulnerability Analysis of Face Morphing Attacks from Landmarks and Generative Adversarial Networks","date":"2020-12-09","arxiv_id":"2012.05344","n_code_links":1,"syntology":null},{"paper":"/paper/practical-no-box-adversarial-attacks-against-1","slug":"practical-no-box-adversarial-attacks-against-1","title":"Practical No-box Adversarial Attacks against DNNs","date":"2020-12-04","arxiv_id":"2012.02525","n_code_links":2,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["qizhangli/nobox-attacks"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"faceguard-a-self-supervised-defense-against","title":"FaceGuard: A Self-Supervised Defense Against Adversarial Face Images","date":"2020-11-28","arxiv_id":"2011.14218","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-attacks-on-deep-learning-face","title":"Robust Attacks on Deep Learning Face Recognition in the Physical World","date":"2020-11-27","arxiv_id":"2011.13526","n_code_links":0,"syntology":null},{"paper":"/paper/google-landmark-recognition-2020-competition","slug":"google-landmark-recognition-2020-competition","title":"Google Landmark Recognition 2020 Competition Third Place Solution","date":"2020-10-11","arxiv_id":"2010.05350","n_code_links":2,"syntology":null},{"paper":"/paper/partial-fc-training-10-million-identities-on","slug":"partial-fc-training-10-million-identities-on","title":"Partial FC: Training 10 Million Identities on a Single Machine","date":"2020-10-11","arxiv_id":"2010.05222","n_code_links":7,"syntology":null},{"paper":"/paper/self-attention-aggregation-network-for-video","slug":"self-attention-aggregation-network-for-video","title":"Self-attention aggregation network for video face representation and recognition","date":"2020-10-11","arxiv_id":"2010.05340","n_code_links":1,"syntology":null},{"paper":"/paper/a2-link-recognizing-disguised-faces-via","slug":"a2-link-recognizing-disguised-faces-via","title":"A2-LINK: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain Knowledge","date":"2020-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"global-local-gcn-large-scale-label-noise","title":"Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition","date":"2020-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-racial-bias-within-face-recognition","title":"Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation","date":"2020-04-19","arxiv_id":"2004.08945","n_code_links":0,"syntology":null},{"paper":"/paper/google-landmarks-dataset-v2-a-large-scale","slug":"google-landmarks-dataset-v2-a-large-scale","title":"Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval","date":"2020-04-03","arxiv_id":"2004.01804","n_code_links":5,"syntology":null},{"paper":"/paper/distribution-distillation-loss-generic","slug":"distribution-distillation-loss-generic","title":"Improving Face Recognition from Hard Samples via Distribution Distillation Loss","date":"2020-02-10","arxiv_id":"2002.03662","n_code_links":2,"syntology":null},{"paper":null,"slug":"investigating-the-impact-of-inclusion-in-face","title":"Investigating the Impact of Inclusion in Face Recognition Training Data on Individual Face Identification","date":"2020-01-09","arxiv_id":"2001.03071","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-adversarial-patches-real-world-attack-on","title":"On adversarial patches: real-world attack on ArcFace-100 face recognition system","date":"2019-10-15","arxiv_id":"1910.07067","n_code_links":0,"syntology":null},{"paper":"/paper/expression-affect-action-unit-recognition-aff","slug":"expression-affect-action-unit-recognition-aff","title":"Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace","date":"2019-09-25","arxiv_id":"1910.04855","n_code_links":0,"syntology":null},{"paper":"/paper/advhat-real-world-adversarial-attack-on","slug":"advhat-real-world-adversarial-attack-on","title":"AdvHat: Real-world adversarial attack on ArcFace Face ID system","date":"2019-08-23","arxiv_id":"1908.08705","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["papermsucode/advhat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"hard-mining-loss-based-convolutional-neural","title":"Hard-Mining Loss based Convolutional Neural Network for Face Recognition","date":"2019-08-09","arxiv_id":"1908.09747","n_code_links":0,"syntology":null},{"paper":null,"slug":"softmax-dissection-towards-understanding","title":"Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning","date":"2019-08-04","arxiv_id":"1908.01281","n_code_links":0,"syntology":null},{"paper":"/paper/airfacelightweight-and-efficient-model-for","slug":"airfacelightweight-and-efficient-model-for","title":"AirFace: Lightweight and Efficient Model for Face Recognition","date":"2019-07-29","arxiv_id":"1907.12256","n_code_links":1,"syntology":null},{"paper":"/paper/a-new-loss-function-for-cnn-classifier-based","slug":"a-new-loss-function-for-cnn-classifier-based","title":"A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids","date":"2019-04-12","arxiv_id":"1904.06008","n_code_links":1,"syntology":null},{"paper":"/paper/a-performance-comparison-of-loss-functions","slug":"a-performance-comparison-of-loss-functions","title":"A Performance Comparison of Loss Functions for Deep Face Recognition","date":"2019-01-01","arxiv_id":"1901.05903","n_code_links":1,"syntology":null},{"paper":"/paper/arcface-additive-angular-margin-loss-for-deep","slug":"arcface-additive-angular-margin-loss-for-deep","title":"ArcFace: Additive Angular Margin Loss for Deep Face Recognition","date":"2018-01-23","arxiv_id":"1801.07698","n_code_links":100,"syntology":{"ran":16,"of":21,"n_ran_checked":2,"n_instrument":14,"unverified":5,"pointer_only":14,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified","official":{"repos":["deepinsight/insightface"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}],"papers_shown":94,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":94,"with_a_code_link":40,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":94,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/method/arcface/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/arcface/papers/ran/1","json":"/method/arcface/papers/ran/1.json","rows":9}],"tasks":[{"task":"/task/face-recognition","name":"Face Recognition","papers":51},{"task":"/task/face-verification","name":"Face Verification","papers":14},{"task":"/task/retrieval","name":"Retrieval","papers":8},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":6},{"task":"/task/representation-learning","name":"Representation Learning","papers":6},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":6},{"task":"/task/attribute","name":"Attribute","papers":5},{"task":"/task/face-identification","name":"Face Identification","papers":5},{"task":"/task/tar","name":"TAR","papers":5},{"task":null,"name":"Triplet","papers":5},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":4},{"task":"/task/landmark-recognition","name":"Landmark Recognition","papers":4},{"task":"/task/diversity","name":"Diversity","papers":3},{"task":"/task/image-classification","name":"Image Classification","papers":3},{"task":"/task/image-generation","name":"Image Generation","papers":3},{"task":"/task/metric-learning","name":"Metric Learning","papers":3},{"task":"/task/clustering","name":"Clustering","papers":2},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":2},{"task":"/task/emotion-recognition","name":"Emotion Recognition","papers":2}],"tasks_shown":20,"n_tasks":100,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":8},{"year":"2020","papers":14},{"year":"2021","papers":19},{"year":"2022","papers":14},{"year":"2023","papers":23},{"year":"2024","papers":10},{"year":"2025","papers":5}],"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/arcface"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=ArcFace","read_at":"2026-10-05T00:52:31+00:00","query":"ArcFace","kind":"paper","have":"unverified_code","tier":"harvested","verified_implementation":false,"level":1,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"1801.07698"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"1801.07698","repositories":{"listed":100,"in_graph":100,"list_truncated":false,"strongest_link":"official"},"retrieve_with":"get_harvested_code_for_paper(arxiv_id='1801.07698')","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"1801.07698","citations":275},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'ArcFace'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"1801.07698","page":"/paper/arcface-additive-angular-margin-loss-for-deep","syntology_url":"https://syntology.ai/paper/1801.07698","in_graph_layer":true,"samples":21,"ran":16,"n_ran_checked":2,"n_instrument":14,"unverified":5,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 5 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"harvested code stored, below machine verification (unverified_code; harvested), served level V1. Repositories: 100 listed of 100 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:1801.07698, not a method entry. This answer is about arXiv:1801.07698, the paper the archive credits with this method.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"890cdbd0058ec3ddb0d82e38e4c1774c42ca524fb0a6f444c179baff7229b303","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}