Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Discussion
Conclusion
References

SDFR: Synthetic Data for Face Recognition Competition

Profile image of Bernardo BiesseckBernardo Biesseck

2024, arXiv (Cornell University)

https://doi.org/10.48550/ARXIV.2404.04580
visibility

…

description

9 pages

link

1 file

Abstract

Large-scale face recognition datasets are collected by crawling the Internet and without individuals' consent, raising legal, ethical, and privacy concerns. With the recent advances in generative models, recently several works proposed generating synthetic face recognition datasets to mitigate concerns in web-crawled face recognition datasets. This paper presents the summary of the Synthetic Data for Face Recognition (SDFR) Competition held in conjunction with the 18th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2024) and established to investigate the use of synthetic data for training face recognition models. The SDFR competition was split into two tasks, allowing participants to train face recognition systems using new synthetic datasets and/or existing ones. In the first task, the face recognition backbone was fixed and the dataset size was limited, while the second task provided almost complete freedom on the model backbone, the dataset, and the training pipeline. The submitted models were trained on existing and also new synthetic datasets and used clever methods to improve training with synthetic data. The submissions were evaluated and ranked on a diverse set of seven benchmarking datasets. The paper gives an overview of the submitted face recognition models and reports achieved performance compared to baseline models trained on real and synthetic datasets. Furthermore, the evaluation of submissions is extended to bias assessment across different demography groups. Lastly, an outlook on the current state of the research in training face recognition models using synthetic data is presented, and existing problems as well as potential future directions are also discussed.

Related papers

SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributes
Georgia Baltsou

arXiv (Cornell University), 2024

AI systems rely on extensive training on large datasets to address various tasks. However, image-based systems, particularly those used for demographic attribute prediction, face significant challenges. Many current face image datasets primarily focus on demographic factors such as age, gender, and skin tone, overlooking other crucial facial attributes like hairstyle and accessories. This narrow focus limits the diversity of the data and consequently the robustness of AI systems trained on them. This work aims to address this limitation by proposing a methodology for generating synthetic face image datasets that capture a broader spectrum of facial diversity. Specifically, our approach integrates a systematic prompt formulation strategy, encompassing not only demographics and biometrics but also non-permanent traits like make-up, hairstyle, and accessories. These prompts guide a state-of-theart text-to-image model in generating a comprehensive dataset of high-quality realistic images and can be used as an evaluation set in face analysis systems. Compared to existing datasets, our proposed dataset proves equally or more challenging in image classification tasks while being much smaller in size.

View PDFchevron_right
Generative Adversarial Network-Based Face Recognition Dataset Generation
Sinwoo Yoo

2018

Facial recognition technique has many advantages than other biometric recognition solutions and recent studies and outcomes of automation process level almost the same as a human does. Applying Deep-Learning solution in this region is very common these days, but there are many obstacles to put in. This paper deals one of them of which the preparation of a certain scale of a dataset by combining existing dataset and another dataset this paper suggests. Celeb A and 2nd version of VGG face dataset are the base dataset that the discriminator agent of Generative Adversarial Network can be trained, and the generator will refer the new dataset with thousands of western portraits we added. This suggested new dataset is tested with Deep-face network as the one of existing facial recognition solutions, and we confirmed that we can use this technique for other similar dataset preprocessing layers. There are some facts to need to consider when it applies to other targets, as analyzed difference...

View PDFchevron_right
State-of-the-art face recognition performance using publicly available software and datasets
Dijana Petrovska-delacrétaz

2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2018

We are interested in the reproducibility of face recognition systems. By reproducibility we mean: is the scientific community, and are the researchers from different sides, capable of reproducing the last published results by a big company, that has at its disposal huge computational power and huge proprietary databases? With the constant advancements in GPU computation power and availability of open-source software, the reproducibility of published results should not be a problem. But, if architectures of the systems are private and databases are proprietary, the reproducibility of published results can not be easily attained. To tackle this problem, we focus on training and evaluation of face recognition systems on publicly available data and software. We are also interested in comparing the best Deep Neural Net (DNN) based results with a baseline "classical" system. This paper exploits the OpenFace open-source system to generate a deep convolutional neural network model using publicly available datasets. We study the impact of the size of the datasets, their quality and compare the performance to a classical face recognition approach. Our focus is to have a fully reproducible model. To this end, we used publicly available datasets (FRGC, MS-celeb-1M, MOBIO, LFW), as well publicly available software (OpenFace) to train our model in order to do face recognition. Our best trained model achieves 97.52% accuracy on the Labelled in the Wild dataset (LFW) dataset which is lower than Google's best reported results of 99.96% but slightly better than FaceBook's reported result of 97.35%. We also evaluated our best model on the challenging video dataset MOBIO and report competitive results with the best reported results on this database.

View PDFchevron_right
Synthetic Data for the Mitigation of Demographic Biases in Face Recognition
Dominik Lawatsch

arXiv (Cornell University), 2024

This study investigates the possibility of mitigating the demographic biases that affect face recognition technologies through the use of synthetic data. Demographic biases have the potential to impact individuals from specific demographic groups, and can be identified by observing disparate performance of face recognition systems across demographic groups. They primarily arise from the unequal representations of demographic groups in the training data. In recent times, synthetic data have emerged as a solution to some problems that affect face recognition systems. In particular, during the generation process it is possible to specify the desired demographic and facial attributes of images, in order to control the demographic distribution of the synthesized dataset, and fairly represent the different demographic groups. We propose to fine-tune with synthetic data existing face recognition systems that present some demographic biases. We use synthetic datasets generated with GANDiffFace, a novel framework able to synthesize datasets for face recognition with controllable demographic distribution and realistic intra-class variations. We consider multiple datasets representing different demographic groups for training and evaluation. Also, we fine-tune different face recognition systems, and evaluate their demographic fairness with different metrics. Our results support the proposed approach and the use of synthetic data to mitigate demographic biases in face recognition.

View PDFchevron_right
Enhancing Face Recognition Dataset using Generative Artificial Intelligence: Review Study
IJCSMC Journal

International Journal of Computer Science and Mobile Computing (IJCSMC), 2025

Face recognition is a fast growing and crucial area of study due to its applicability in different life applications. Face recognition systems often face significant challenges due to poor-quality datasets, which can result from factors such as low illumination, low resolution, facial distortions, and varying environmental conditions. These limitations hinder the performance and reliability of face recognition technologies. Generative Adversarial Networks (GANs) have emerged as a powerful tool to address these issues by enhancing image quality and generating realistic facial representations under challenging conditions. This review paper explores various GAN-based models each designed to tackle specific face recognition challenges. These models demonstrate significant improvements in enhancement ratios, ranging from 75% to 97%, by leveraging advanced generative techniques to reconstruct and augment facial images. Beyond face recognition, the methodologies discussed in this research have broader implications for enhancing image datasets in other domains, such as medical imaging, surveillance, and autonomous driving, where poor data quality is a common issue. By improving dataset quality through generative AI, this research paves the way for more robust and accurate machine learning applications across diverse fields.

View PDFchevron_right
SREFI: Synthesis of realistic example face images
john bernhard

2017 IEEE International Joint Conference on Biometrics (IJCB), 2017

In this paper, we propose a novel face synthesis approach that can generate an arbitrarily large number of synthetic images of both real and synthetic identities. Thus a face image dataset can be expanded in terms of the number of identities represented and the number of images per identity using this approach, without the identity-labeling and privacy complications that come from downloading images from the web. To measure the visual fidelity and uniqueness of the synthetic face images and identities, we conducted face matching experiments with both human participants and a CNN pre-trained on a dataset of 2.6M real face images. To evaluate the stability of these synthetic faces, we trained a CNN model with an augmented dataset containing close to 200,000 synthetic faces. We used a snapshot of this trained CNN to recognize extremely challenging frontal (real) face images. Experiments showed training with the augmented faces boosted the face recognition performance of the CNN.

View PDFchevron_right
Face-Specific Data Augmentation for Unconstrained Face Recognition
Anh Tú Trần

International Journal of Computer Vision

We identify two issues as key to developing effective face recognition systems: maximizing the appearance variations of training images and minimizing appearance variations in test images. The former is required to train the system for whatever appearance variations it will ultimately encounter and is often addressed by collecting massive training sets with millions of face images. The latter involves various forms of appearance normalization for removing distracting nuisance factors at test time and making test faces easier to compare. We describe novel, efficient face-specific data augmentation techniques and show them to be ideally suited for both purposes. By using knowledge of faces, their 3D shapes, and appearances, we show the following: (a) We can artificially enrich training data for face recognition with face-specific appearance variations. (b) This synthetic training data can be efficiently produced online, thereby reducing the massive storage requirements of large-scale training sets and simplifying training for many appearance variations. Finally, (c) The same, fast data augmentation techniques can be applied at test time to reduce appearance variations and improve face representations. Together, with additional technical novelties, we describe a highly effective face recognition pipeline which, at the time of submission, obtains state-of-the-art results across multiple benchmarks. Portions of this paper were previously published by Masi et al. (European conference on computer vision, Springer, pp 579-596, 2016b, International conference on automatic face and gesture recognition, 2017).

View PDFchevron_right
Face recognition for web-scale datasets
Enrique Ortiz

Computer Vision and Image Understanding, 2014

With millions of users and billions of photos, web-scale face recognition is a challenging task that demands speed, accuracy, and scalability. Most current approaches do not address and do not scale well to Internet-sized scenarios such as tagging friends or finding celebrities. Focusing on web-scale face identification, we gather an 800,000 face dataset from the Facebook social network that models real-world situations where specific faces must be recognized and unknown identities rejected. We propose a novel Linearly Approximated Sparse Representation-based Classification (LASRC) algorithm that uses linear regression to perform sample selection for ' 1 -minimization, thus harnessing the speed of least-squares and the robustness of sparse solutions such as SRC. Our efficient LASRC algorithm achieves comparable performance to SRC with a 100-250 times speedup and exhibits similar recall to SVMs with much faster training. Extensive tests demonstrate our proposed approach is competitive on pair-matching verification tasks and outperforms current state-of-the-art algorithms on open-universe identification in uncontrolled, web-scale scenarios.

View PDFchevron_right
Knowing the Distance: Understanding the Gap Between Synthetic and Real Data For Face Parsing
assaf lehr

arXiv (Cornell University), 2023

The use of synthetic data for training computer vision algorithms has become increasingly popular due to its cost-effectiveness, scalability, and ability to provide accurate multi-modality labels. Although recent studies have demonstrated impressive results when training networks solely on synthetic data, there remains a performance gap between synthetic and real data that is commonly attributed to lack of photorealism. The aim of this study is to investigate the gap in greater detail for the face parsing task. We differentiate between three types of gaps: distribution gap, label gap, and photorealism gap. Our findings show that the distribution gap is the largest contributor to the performance gap, accounting for over 50% of the gap. By addressing this gap and accounting for the labels gap, we demonstrate that a model trained on synthetic data achieves comparable results to one trained on a similar amount of real data. This suggests that synthetic data is a viable alternative to real data, especially when real data is limited or difficult to obtain. Our study highlights the importance of content diversity in synthetic datasets and challenges the notion that the photorealism gap is the most critical factor affecting the performance of computer vision models trained on synthetic data.

View PDFchevron_right
Dataset bias exposed in face verification
Eric Lopez

IET Biometrics, 2019

Most facial verification methods assume that training and testing sets contain independent and identically distributed samples, although, in many real applications, this assumption does not hold. Whenever gathering a representative dataset in the target domain is unfeasible, it is necessary to choose one of the already available (source domain) datasets. In this paper, a study was performed over the differences among six public datasets, and how this impacts on the performance of the learned methods. In the considered scenario of mobile devices, the individual of interest is enrolled using a few facial images taken in the operational domain, while training impostors are drawn from one of the public available datasets. This work tried to shed light on the inherent differences among the datasets, and potential harms that should be considered when they are combined for training and testing. Results indicate that a drop in performance occurs whenever training and testing are done on different datasets compared to the case of using the same dataset in both phases. However, the decay strongly depends on the kind of features. Besides, the representation of samples in the feature space reveals insights into to what extent bias is an endogenous or an exogenous factor.

View PDFchevron_right

References (49)

  1. The rise and fall (and rise) of datasets. Nature Machine Intelligence, 4(1):1-2, 2022.
  2. G. Bae, M. de La Gorce, T. Baltrušaitis, C. Hewitt, D. Chen, J. Valentin, R. Cipolla, and J. Shen. DigiFace-1M: 1 million digital face images for face recognition. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 3526-3535, 2023.
  3. V. N. Boddeti, G. Sreekumar, and A. Ross. On the biometric capacity of generative face models. In Proceedings of the IEEE International Joint Conference on Biometrics (IJCB), pages 1-10. IEEE, 2023.
  4. F. Boutros, N. Damer, J. N. Kolf, K. Raja, F. Kirchbuchner, R. Ra- machandra, A. Kuijper, P. Fang, C. Zhang, F. Wang, D. Montero, N. Aginako, B. Sierra, M. Nieto, M. E. Erakin, U. Demir, H. K. Ekenel, A. Kataoka, K. Ichikawa, S. Kubo, J. Zhang, M. He, D. Han, S. Shan, K. Grm, V. Štruc, S. Seneviratne, N. Kasthuriarachchi, S. Rasnayaka, P. C. Neto, A. F. Sequeira, J. R. Pinto, M. Saffari, and J. S. Cardoso. MFR 2021: Masked face recognition competition. In Proceedings of the IEEE International joint conference on biometrics (IJCB), pages 1-10. IEEE, 2021.
  5. F. Boutros, J. H. Grebe, A. Kuijper, and N. Damer. IDiff-Face: Synthetic-based face recognition through fizzy identity-conditioned diffusion model. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 19650-19661, 2023.
  6. F. Boutros, M. Huber, P. Siebke, T. Rieber, and N. Damer. SFace: Privacy-friendly and accurate face recognition using synthetic data. In Proceedings of the IEEE International Joint Conference on Biometrics (IJCB), pages 1-11. IEEE, 2022.
  7. F. Boutros, M. Klemt, M. Fang, A. Kuijper, and N. Damer. Unsuper- vised face recognition using unlabeled synthetic data. In Proceedings of the IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG), pages 1-8. IEEE, 2023.
  8. F. Boutros, V. Struc, J. Fierrez, and N. Damer. Synthetic data for face recognition: Current state and future prospects. Image and Vision Computing, page 104688, 2023.
  9. Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and A. Zisserman. VGGFace2: A dataset for recognising faces across pose and age. In Proceedings of the 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG), pages 67-74. IEEE, 2018.
  10. S. Cheng, P. Ma, G. Tzimiropoulos, S. Petridis, A. Bulat, J. Shen, and M. Pantic. Towards pose-invariant lip-reading. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 4357-4361. IEEE, 2020.
  11. L. Colbois, T. de Freitas Pereira, and S. Marcel. On the use of automatically generated synthetic image datasets for benchmarking face recognition. In Proceedings of the IEEE International Joint Conference on Biometrics (IJCB), pages 1-8. IEEE, 2021.
  12. E. D. Cubuk, B. Zoph, J. Shlens, and Q. V. Le. Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 702-703, 2020.
  13. J. Deng, J. Guo, X. An, Z. Zhu, and S. Zafeiriou. Masked face recog- nition challenge: The insightface track report. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pages 1437-1444, 2021.
  14. J. Deng, J. Guo, N. Xue, and S. Zafeiriou. ArcFace: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4690- 4699, 2019.
  15. J. Deng, J. Guo, D. Zhang, Y. Deng, X. Lu, and S. Shi. Lightweight face recognition challenge. In Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision Workshops (ICCVW), 2019.
  16. A. George, C. Ecabert, H. O. Shahreza, K. Kotwal, and S. Marcel. EdgeFace: Efficient face recognition model for edge devices. IEEE Transactions on Biometrics, Behavior, and Identity Science, 6(2):158- 168, 2024.
  17. Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao. MS-Celeb-1M: A dataset and benchmark for large-scale face recognition. In Proceedings of the European Conference on Computer Vision (ECCV), pages 87-102.
  18. G. B. Huang, M. Mattar, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. In Workshop on faces in'Real-Life'Images: detection, alignment, and recognition, 2008.
  19. K. Karkkainen and J. Joo. FairFace: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 1548-1558, 2021.
  20. T. Karras, M. Aittala, J. Hellsten, S. Laine, J. Lehtinen, and T. Aila. Training generative adversarial networks with limited data. Advances in Neural Information Processing Systems, 33:12104-12114, 2020.
  21. T. Karras, M. Aittala, S. Laine, E. Härkönen, J. Hellsten, J. Lehtinen, and T. Aila. Alias-free generative adversarial networks. Advances in Neural Information Processing Systems, 34:852-863, 2021.
  22. T. Karras, S. Laine, and T. Aila. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4401-4410, 2019.
  23. M. Kim, A. K. Jain, and X. Liu. AdaFace: Quality adaptive margin for face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 18750- 18759, 2022.
  24. M. Kim, F. Liu, A. Jain, and X. Liu. DCFace: Synthetic face generation with dual condition diffusion model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12715-12725, 2023.
  25. J. N. Kolf, F. Boutros, J. Elliesen, M. Theuerkauf, N. Damer, M. Alansari, O. A. Hay, S. Alansari, S. Javed, N. Werghi, K. Grm, V. Štruc, F. Alonso-Fernandez, K. H. Diaz, J. Bigun, A. George, C. Ecabert, H. O. Shahreza, K. Kotwal, S. Marcel, I. Medvedev, B. Jin, D. Nunes, A. Hassanpour, P. Khatiwada, A. A. Toor, and B. Yang. EFaR 2023: Efficient face recognition competition. In Proceedings of the IEEE International Joint Conference on Biometrics (IJCB), pages 1-12. IEEE, 2023.
  26. J. N. Kolf, T. Rieber, J. Elliesen, F. Boutros, A. Kuijper, and N. Damer. Identity-driven three-player generative adversarial network for synthetic-based face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 806-816, 2023.
  27. C. Kong, Q. Luo, and G. Chen. RSFAD: A large-scale real scenario face age dataset in the wild. In 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pages 1-7. IEEE, 2021.
  28. B. Maze, J. Adams, J. A. Duncan, N. Kalka, T. Miller, C. Otto, A. K. Jain, W. T. Niggel, J. Anderson, J. Cheney, et al. IARPA janus benchmark-c: Face dataset and protocol. In Proceedings of the International Conference on Biometrics (ICB), pages 158-165. IEEE, 2018.
  29. P. Melzi, C. Rathgeb, R. Tolosana, R. Vera-Rodriguez, D. Lawatsch, F. Domin, and M. Schaubert. GANDiffFace: Controllable generation of synthetic datasets for face recognition with realistic variations. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pages 3086-3095, 2023.
  30. P. Melzi, R. Tolosana, R. Vera-Rodriguez, M. Kim, C. Rathgeb, X. Liu, I. DeAndres-Tame, A. Morales, J. Fierrez, J. Ortega-Garcia, W. Zhao, X. Zhu, Z. Yan, X.-Y. Zhang, J. Wu, Z. Lei, S. Tripathi, M. Kothari, M. H. Zama, D. Deb, B. Biesseck, P. Vidal, R. Granada, G. Fickel, G. Führ, D. Menotti, A. Unnervik, A. George, C. Ecabert, H. O. Shahreza, P. Rahimi, S. Marcel, I. Sarridis, C. Koutlis, G. Baltsou, S. Papadopoulos, C. Diou, N. D. Domenico, G. Borghi, L. Pelle- grini, E. Mas-Candela, Ángela Sánchez-Pérez, A. Atzori, F. Boutros, N. Damer, G. Fenu, and M. Marras. FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems. Information Fusion, 107:102322, 2024.
  31. P. Melzi, R. Tolosana, R. Vera-Rodriguez, M. Kim, C. Rathgeb, X. Liu, I. DeAndres-Tame, A. Morales, J. Fierrez, J. Ortega-Garcia, W. Zhao, X. Zhu, Z. Yan, X.-Y. Zhang, J. Wu, Z. Lei, S. Tripathi, M. Kothari, M. H. Zama, D. Deb, B. Biesseck, P. Vidal, R. Granada, G. Fickel, G. Führ, D. Menotti, A. Unnervik, A. George, C. Ecabert, H. O. Shahreza, P. Rahimi, S. Marcel, I. Sarridis, C. Koutlis, G. Baltsou, S. Papadopoulos, C. Diou, N. D. Domenico, G. Borghi, L. Pelle- grini, E. Mas-Candela, Ángela Sánchez-Pérez, A. Atzori, F. Boutros, N. Damer, G. Fenu, and M. Marras. FRCSyn challenge at WACV 2024: Face recognition challenge in the era of synthetic data. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), pages 892-901, 2024.
  32. Q. Meng, S. Zhao, Z. Huang, and F. Zhou. MagFace: A universal representation for face recognition and quality assessment. In Pro- ceedings of the IEEE/CVF Conference on Computer Vsion and Pattern Recognition (CVPR), pages 14225-14234, 2021.
  33. S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia, and S. Zafeiriou. AgeDB: the first manually collected, in-the-wild age database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 51-59, 2017.
  34. H. Qiu, B. Yu, D. Gong, Z. Li, W. Liu, and D. Tao. SynFace: Face recognition with synthetic data. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 10880- 10890, 2021.
  35. R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10684-10695, 2022.
  36. N. Ruiz, Y. Li, V. Jampani, Y. Pritch, M. Rubinstein, and K. Aberman. DreamBooth: Fine tuning text-to-image diffusion models for subject- driven generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 22500- 22510, 2023.
  37. C. Schuhmann, R. Beaumont, R. Vencu, C. Gordon, R. Wightman, M. Cherti, T. Coombes, A. Katta, C. Mullis, M. Wortsman, et al. LAION-5B: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, 35:25278-25294, 2022.
  38. H. O. Shahreza, A. George, and S. Marcel. SynthDistill: Face recogni- tion with knowledge distillation from synthetic data. In Proceedings of the IEEE International Joint Conference on Biometrics (IJCB), pages 1-10. IEEE, 2023.
  39. H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li, and W. Liu. CosFace: Large margin cosine loss for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 5265-5274, 2018.
  40. M. Wang, W. Deng, J. Hu, X. Tao, and Y. Huang. Racial faces in the wild: Reducing racial bias by information maximization adaptation network. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 692-702, 2019.
  41. C. Whitelam, E. Taborsky, A. Blanton, B. Maze, J. Adams, T. Miller, N. Kalka, A. K. Jain, J. A. Duncan, K. Allen, et al. IARPA janus benchmark-b face dataset. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 90-98, 2017.
  42. Y. Yang, Y. lin, H. Liu, W. Shao, R. Chen, H. Shang, Y. Wang, Y. Qiao, K. Zhang, and P. Luo. Towards implicit prompt for text-to-image models, 2024.
  43. D. Yi, Z. Lei, S. Liao, and S. Z. Li. Learning face representation from scratch. arXiv preprint arXiv:1411.7923, 2014.
  44. K. Zhang, Z. Zhang, Z. Li, and Y. Qiao. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10):1499-1503, 2016.
  45. T. Zheng and W. Deng. Cross-Pose LFW: A database for studying cross-pose face recognition in unconstrained environments. Beijing University of Posts and Telecommunications, Tech. Rep, 5(7), 2018.
  46. T. Zheng, W. Deng, and J. Hu. Cross-Age LFW: A database for studying cross-age face recognition in unconstrained environments. arXiv preprint arXiv:1708.08197, 2017.
  47. Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang. Random erasing data augmentation. In Proceedings of the AAAI conference on Artificial Intelligence, volume 34, pages 13001-13008, 2020.
  48. X. Zhu, X. Liu, Z. Lei, and S. Z. Li. Face alignment in full pose range: A 3d total solution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(1):78-92, 2017.
  49. Z. Zhu, G. Huang, J. Deng, Y. Ye, J. Huang, X. Chen, J. Zhu, T. Yang, J. Lu, D. Du, et al. WebFace260M: A benchmark unveiling the power of million-scale deep face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10492-10502, 2021.

Related papers

Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Bernardo Biesseck

arXiv (Cornell University), 2024

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 intraclass variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2 nd 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 1 st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2 nd edition we propose new subtasks that allow participants to explore novel face generative methods. The outcomes of the 2 nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.

View PDFchevron_right
FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data
Georgia Baltsou

arXiv (Cornell University), 2023

Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail. This paper offers an overview of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at WACV 2024. This is the first international challenge aiming to explore the use of synthetic data in face recognition to address existing limitations in the technology. Specifically, the FRCSyn Challenge targets concerns related to data privacy issues, demographic biases, generalization to unseen scenarios, and performance limitations in challenging scenarios, including significant age disparities between enrollment and testing, pose variations, and occlusions. The results achieved in the FRCSyn Challenge, together with the proposed benchmark, contribute significantly to the application of synthetic data to improve face recognition technology.

View PDFchevron_right
GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations
Dominik Lawatsch

arXiv (Cornell University), 2023

Face recognition systems have significantly advanced in recent years, driven by the availability of large-scale datasets. However, several issues have recently came up, including privacy concerns that have led to the discontinuation of well-established public datasets. Synthetic datasets have emerged as a solution, even though current synthesis methods present other drawbacks such as limited intraclass variations, lack of realism, and unfair representation of demographic groups. This study introduces GAN-DiffFace, a novel framework for the generation of synthetic datasets for face recognition that combines the power of Generative Adversarial Networks (GANs) and Diffusion models to overcome the limitations of existing synthetic datasets. In GANDiffFace, we first propose the use of GANs to synthesize highly realistic identities and meet target demographic distributions. Subsequently, we fine-tune Diffusion models with the images generated with GANs, synthesizing multiple images of the same identity with a variety of accessories, poses, expressions, and contexts. We generate multiple synthetic datasets by changing GANDiffFace settings, and compare their mated and non-mated score distributions with the distributions provided by popular realworld datasets for face recognition, i.e. VGG2 and IJB-C. Our results show the feasibility of the proposed GANDiff-Face, in particular the use of Diffusion models to enhance the (limited) intra-class variations provided by GANs towards the level of real-world datasets.

View PDFchevron_right
Generating photo-realistic training data to improve face recognition accuracy
Daniel Trigueros

Neural Networks, 2021

Face recognition has become a widely adopted biometric in forensics, security and law enforcement thanks to the high accuracy achieved by systems based on convolutional neural networks (CNNs). However, to achieve good performance, CNNs need to be trained with very large datasets which are not always available. In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete identity labels to an identity latent space that follows a simple prior distribution, and training a GAN conditioned on samples from that distribution. A main novelty of our approach is the ability to generate both synthetic images of subjects in the training set and synthetic images of new subjects not in the training set, both of which we use to augment face datasets. By using recent advances in GAN training, we show that the synthetic images generated by our model are photo-realistic, and that training with datasets augmented with those images can lead to increased recognition accuracy. Experimental results show that our method is more effective when augmenting small datasets. In particular, an absolute accuracy improvement of 8.42% was

View PDFchevron_right
DigiFace-1M: 1 Million Digital Face Images for Face Recognition
Martin Gorce

arXiv (Cornell University), 2022

State-of-the-art face recognition models show impressive accuracy, achieving over 99.8% on Labeled Faces in the Wild (LFW) dataset. Such models are trained on large-scale datasets that contain millions of real human face images collected from the internet. Web-crawled face images are severely biased (in terms of race, lighting, make-up, etc) and often contain label noise. More importantly, the face images are collected without explicit consent, raising ethical concerns. To avoid such problems, we introduce a largescale synthetic dataset for face recognition, obtained by rendering digital faces using a computer graphics pipeline 1. We first demonstrate that aggressive data augmentation can significantly reduce the synthetic-to-real domain gap. Having full control over the rendering pipeline, we also study how each attribute (e.g., variation in facial pose, accessories and textures) affects the accuracy. Compared to Syn-Face, a recent method trained on GAN-generated synthetic faces, we reduce the error rate on LFW by 52.5% (accuracy from 91.93% to 96.17%). By fine-tuning the network on a smaller number of real face images that could reasonably be obtained with consent, we achieve accuracy that is comparable to the methods trained on millions of real face images.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved