mlsanityData to 7 Oct 2026

CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

arXiv 2004.00288 ↗First posted 1 Apr 2020cs.CVcited by 320

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability. More recently, the idea of mining-based strategies is adopted to emphasize the misclassified samples, achieving promising results. However, during the entire training process, the prior methods either do not explicitly emphasize the sample based on its importance that renders the hard samples not fully exploited; or explicitly emphasize the effects of semi-hard/hard samples even at the early training stage that may lead to convergence issue. In this work, we propose a novel Adaptive Curriculum Learning loss (CurricularFace) that embeds the idea of curriculum learning into the loss function to achieve a novel training strategy for deep face recognition, which mainly addresses easy samples in the early training stage and hard ones in the later stage. Specifically, our CurricularFace adaptively adjusts the relative importance of easy and hard samples during different training stages. In each stage, different samples are assigned with different importance according to their corresponding difficultness. Extensive experimental results on popular benchmarks demonstrate the superiority of our CurricularFace over the state-of-the-art competitors.

Key facts. Cited by 320 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 59; 2023: 79; 2024: 55; 2025: 49; 2026: 32.

320 papers.

Sort:

By area:

  1. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
  2. 2021Curriculum Learning: A Surveycited by 257
  3. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  4. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 221
  5. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  6. 2023Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Modelscited by 203
  7. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 155
  8. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
  9. 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignmentcited by 143
  10. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 126
  11. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  12. 2021HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swappingcited by 92
38 more
  1. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  2. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  3. 2025DreamO: A Unified Framework for Image Customizationcited by 82
  4. 2021HairCLIP: Design Your Hair by Text and Reference Imagecited by 79
  5. 2023PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalizationcited by 77
  6. 2022Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FCcited by 73
  7. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  8. 2025Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learningcited by 71
  9. 2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 68
  10. 2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
  11. 2024Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Controlcited by 66
  12. 2022SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Datacited by 63
  13. 2021Uncertainty-Aware Unsupervised Domain Adaptation in Object Detectioncited by 59
  14. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  15. 2021FaceX-Zoo: A PyTorch Toolbox for Face Recognitioncited by 49
  16. 2022Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Inputcited by 49
  17. 2023Face Animation with an Attribute-Guided Diffusion Modelcited by 48
  18. 2024LCM-Lookahead for Encoder-based Text-to-Image Personalizationcited by 48
  19. 2022Correlation Verification for Image Retrievalcited by 47
  20. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  21. 2024UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalizationcited by 46
  22. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  23. 20223D GAN Inversion with Pose Optimizationcited by 44
  24. 2023MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoderscited by 44
  25. 2025HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioningcited by 44
  26. 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
  27. 2021Masked Face Recognition Challenge: The InsightFace Track Reportcited by 41
  28. 2022WebFace260M: A Benchmark for Million-Scale Deep Face Recognitioncited by 41
  29. 2023TriPlaneNet: An Encoder for EG3D Inversioncited by 41
  30. 2023Global Features are All You Need for Image Retrieval and Rerankingcited by 41
  31. 2021Consistent Instance False Positive Improves Fairness in Face Recognitioncited by 40
  32. 2023High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learningcited by 37
  33. 2024KeyPoint Relative Position Encoding for Face Recognitioncited by 37
  34. 2023DyGait: Exploiting Dynamic Representations for High-performance Gait Recognitioncited by 35
  35. 2021E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversioncited by 33
  36. 2023EdgeFace: Efficient Face Recognition Model for Edge Devicescited by 33
  37. 2022SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Datacited by 30
  38. 2022Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domaincited by 28

50 most cited of 320 All 320 (JSON)