Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data (2404.10378v1)

Published 16 Apr 2024 in cs.CV, cs.AI, cs.CY, and cs.LG

Abstract: Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new sub-tasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Partial FC: Training 10 Million Identities on a Single Machine. In Proc. IEEE/CVF International Conference on Computer Vision Workshops, 2021.
  2. If It’s Not Enough, Make It So: Reducing Authentic Data Demand in Face Recognition through Synthetic Faces. In Proc. 18th International Conference on Automatic Face and Gesture Recognition, 2024.
  3. DigiFace-1M: 1 Million Digital Face Images for Face Recognition. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision, 2023.
  4. Impact of Deep Learning Approaches on Facial Expression Recognition in Healthcare Industries. IEEE Transactions on Industrial Informatics, 18(8):5619–5627, 2022.
  5. ElasticFace: Elastic Margin Loss for Deep Face Recognition. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.
  6. IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Model. In Proc. IEEE/CVF International Conference on Computer Vision, 2023a.
  7. Unsupervised Face Recognition using Unlabeled Synthetic Data. In Proc. 17th International Conference on Automatic Face and Gesture Recognition, 2023b.
  8. Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers. arXiv preprint arXiv:2401.11605, 2024.
  9. Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models. IEEE Transactions on Artificial Intelligence, pages 1–12, 2023.
  10. MATT: Multimodal Attention Level Estimation for e-learning Platforms. In Proc. AAAI Workshop on Artificial Intelligence for Education, 2023.
  11. How Good Is ChatGPT at Face Biometrics? A First Look Into Recognition, Soft Biometrics, and Explainability. IEEE Access, 12:34390–34401, 2024.
  12. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.
  13. The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances. ACM Comput. Surv., 54(10s), 2022.
  14. Improved Residual Networks for Image and Video Recognition. In Proc. 25th International Conference on Pattern Recognition, 2021.
  15. On Recognizing Occluded Faces in the Wild. In Proc. International Conference of the Biometrics Special Interest Group, 2021.
  16. FaceMix: Transferring Local Regions for Data Augmentation in Face Recognition. In Proc. Neural Information Processing, 2023.
  17. Improving Parkinson Detection Using Dynamic Features From Evoked Expressions in Video. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.
  18. Deep Residual Learning for Image Recognition. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2016.
  19. Squeeze-and-Excitation Networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2018.
  20. Controllable Inversion of Black-Box Face Recognition Models via Diffusion. In Proc. IEEE/CVF International Conference on Computer Vision Workshops, 2023.
  21. A Style-Based Generator Architecture for Generative Adversarial Networks. In Proc. IEEE/CVF conference on Computer Vision and Pattern Recognition, 2019.
  22. Analyzing and Improving the Image Quality of StyleGAN. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
  23. AdaFace: Quality Adaptive Margin for Face Recognition. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
  24. DCFace: Synthetic Face Generation with Dual Condition Diffusion Model. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023.
  25. PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.
  26. SlackedFace: Learning a Slacked Margin for Low-Resolution Face Recognition. In Proc. 34th British Machine Vision Conference, 2023.
  27. GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations. In Proc. IEEE/CVF International Conference on Computer Vision Workshops, 2023a.
  28. Synthetic Data for the Mitigation of Demographic Biases in Face Recognition. In Proc. IEEE International Joint Conference on Biometrics, 2023b.
  29. Multi-IVE: Privacy Enhancement of Multiple Soft-Biometrics in Face Embeddings. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2023c.
  30. FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data. In Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2024a.
  31. FRCSyn-onGoing: Benchmarking and Comprehensive Evaluation of Real and Synthetic Data to Improve Face Recognition Systems. Information Fusion, 107:102322, 2024b.
  32. SensitiveNets: Learning Agnostic Representations with Application to Face Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(6):2158–2164, 2021.
  33. AgeDB: The First Manually Collected, In-The-Wild Age Database. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.
  34. OCFR 2022: Competition on Occluded Face Recognition from Synthetically Generated Structure-Aware Occlusions. In Proc. IEEE International Joint Conference on Biometrics, 2022.
  35. Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition. In Proc. International Conference of the Biometrics Special Interest Group, 2023.
  36. SynFace: Face Recognition with Synthetic Data. In Proc. IEEE/CVF International Conference on Computer Vision, 2021.
  37. Frontal to Profile Face Verification in the Wild. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.
  38. SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data. In Proc. IEEE International Joint Conference on Biometrics, 2023.
  39. SDFR: Synthetic Data for Face Recognition Competition. In Proc. 18th IEEE International Conference on Automatic Face and Gesture Recognition, 2024.
  40. Prototype Memory for Large-Scale Face Representation Learning. IEEE Access, 10:12031–12046, 2022.
  41. Denoising Diffusion Implicit Models. In Proc. International Conference on Learning Representations, 2021.
  42. A Comprehensive Study on Face Recognition Biases Beyond Demographics. IEEE Transactions on Technology and Society, 3(1):16–30, 2021.
  43. StyleNAT: Giving Each Head a New Perspective. arXiv preprint arXiv:2211.05770, 2022.
  44. CosFace: Large Margin Cosine Loss for Deep Face Recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2018.
  45. FaceX-Zoo: A PyTorch Toolbox for Face Recognition. In Proc. 29th ACM International Conference on Multimedia, 2021.
  46. Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
  47. Deep Face Recognition: A Survey. Neurocomputing, 429:215–244, 2021.
  48. Learning Face Representation from Scratch. arXiv preprint arXiv:1411.7923, 2014.
  49. ITI-GEN: Inclusive Text-to-Image Generation. In Proc. IEEE/CVF International Conference on Computer Vision, 2023.
  50. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. IEEE Signal Processing Letters, 23(10):1499–1503, 2016.
  51. SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition. IEEE Transactions on Image Processing, 30:2587–2598, 2021.
  52. UniFace: Unified Cross-Entropy Loss for Deep Face Recognition. In Proc. IEEE/CVF International Conference on Computer Vision, 2023.
  53. WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (58)
  1. Ivan DeAndres-Tame (8 papers)
  2. Ruben Tolosana (79 papers)
  3. Pietro Melzi (10 papers)
  4. Ruben Vera-Rodriguez (66 papers)
  5. Minchul Kim (20 papers)
  6. Christian Rathgeb (52 papers)
  7. Xiaoming Liu (145 papers)
  8. Aythami Morales (93 papers)
  9. Julian Fierrez (131 papers)
  10. Javier Ortega-Garcia (51 papers)
  11. Zhizhou Zhong (8 papers)
  12. Yuge Huang (18 papers)
  13. Yuxi Mi (10 papers)
  14. Shouhong Ding (90 papers)
  15. Shuigeng Zhou (81 papers)
  16. Shuai He (8 papers)
  17. Lingzhi Fu (7 papers)
  18. Heng Cong (9 papers)
  19. Rongyu Zhang (25 papers)
  20. Zhihong Xiao (3 papers)
Citations (12)
View on Semantic Scholar