mlsanityData to 7 Oct 2026

CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition

arXiv 2409.18876 ↗First posted 27 Sep 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Privacy issue is a main concern in developing face recognition techniques. Although synthetic face images can partially mitigate potential legal risks while maintaining effective face recognition (FR) performance, FR models trained by face images synthesized by existing generative approaches frequently suffer from performance degradation problems due to the insufficient discriminative quality of these synthesized samples. In this paper, we systematically investigate what contributes to solid face recognition model training, and reveal that face images with certain degree of similarities to their identity centers show great effectiveness in the performance of trained FR models. Inspired by this, we propose a novel diffusion-based approach (namely Center-based Semi-hard Synthetic Face Generation (CemiFace)) which produces facial samples with various levels of similarity to the subject center, thus allowing to generate face datasets containing effective discriminative samples for training face recognition. Experimental results show that with a modest degree of similarity, training on the generated dataset can produce competitive performance compared to previous generation methods.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 27 Sep 2024.

Builds on

38 of 52 references.

References · 38

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  10. 2016Learning without Forgettingcited by 2,465
  11. 2021Variational Diffusion Modelscited by 1,145
  12. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
26 more
  1. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  2. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  3. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  4. 2014Learning Face Representation from Scratchcited by 451
  5. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  6. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 390
  7. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  8. 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 258
  9. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 221
  10. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 219
  11. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
  12. 2023Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspectivecited by 136
  13. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  14. 2022Efficient Dataset Distillation Using Random Feature Approximationcited by 111
  15. 2021SynFace: Face Recognition with Synthetic Datacited by 106
  16. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  17. 2023IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Modelscited by 72
  18. 2022SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Datacited by 63
  19. 2020On Disentangling Spoof Trace for Generic Face Anti-Spoofingcited by 62
  20. 2023GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variationscited by 49
  21. 2023Face Animation with an Attribute-Guided Diffusion Modelcited by 48
  22. 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
  23. 2023Controllable Inversion of Black-Box Face Recognition Models via Diffusioncited by 22
  24. 2022Part-based Face Recognition with Vision Transformerscited by 18
  25. 2018Comparator Networkscited by 13
  26. 2024LAFS: Landmark-based Facial Self-supervised Learning for Face Recognitioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusioncited by 12
  2. 2025Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromisecited by 8
  3. 2025UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognitioncited by 3
  4. 2025AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognitioncited by 3
  5. 2026IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbationcited by 2
  6. 2025Vec2Face+ for Face Dataset Generationcited by 1
  7. 2026MAUGen: A Unified Diffusion Approach for Multi-Identity Facial Expression and AU Label Generationcited by 0
  8. 2026On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detectioncited by 0
  9. 2026SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbationcited by 0
  10. 2026Benchmarking Face Recognition without Real Facescited by 0