Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy

Trigueros, Daniel Sáez; Li, Meng; Hartnett, Margaret

doi:10.48550/arxiv.1811.00112

Cited by 4 publications

(7 citation statements)

References 52 publications

(88 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A second approach is instead to retrain the generative model to make it conditional. This is generally done by ensuring the latent input to the generator can be split between a component specifying identity and a component specifying all other factors of variations ( [9], [31], [4]), with sometimes a even finer control on the factors of variation to manipulate several semantic attributes in a disentangled manner ( [23], [11]).…”

Section: Synthetic Face Generationmentioning

confidence: 99%

On the use of automatically generated synthetic image datasets for benchmarking face recognition

Colbois,

Pereira,

Marcel

2021

Preprint

View full text Add to dashboard Cite

The availability of large-scale face datasets has been key in the progress of face recognition. However, due to licensing issues or copyright infringement, some datasets are not available anymore (e.g. MS-Celeb-1M). Recent advances in Generative Adversarial Networks (GANs), to synthesize realistic face images, provide a pathway to replace real datasets by synthetic datasets, both to train and benchmark face recognition (FR) systems. The work presented in this paper provides a study on benchmarking FR systems using a synthetic dataset. First, we introduce the proposed methodology to generate a synthetic dataset, without the need for human intervention, by exploiting the latent structure of a StyleGAN2 model with multiple controlled factors of variation. Then, we confirm that (i) the generated synthetic identities are not data subjects from the GAN's training dataset, which is verified on a synthetic dataset with 10K+ identities; (ii) benchmarking results on the synthetic dataset are a good substitution, often providing error rates and system ranking similar to the benchmarking on the real dataset.

show abstract

Section: Synthetic Face Generationmentioning

confidence: 99%

On the use of automatically generated synthetic image datasets for benchmarking face recognition

Colbois,

Pereira,

Marcel

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In this work we evaluate IVI-GAN [18]. However, there are many other works that fall into this category [28,29].…”

Section: Disentanglementmentioning

confidence: 99%

“…We are aware of only a handful of examples of "supervised" data-augmentation using synthetic identities. The works of [29], [6] and [7] each train facial recognition (FR) networks using both real and synthetic identities simultaneously. This makes it important to be sure that new, synthetic identities are being generated to ensure that collisions with existing identities are rare.…”

Section: Data-augmentationmentioning

confidence: 99%

“…For example, with the recent implementation of the General Data Protection Regulation (GDPR) in Europe, a natural question to ask is whether GANs can be used to generate sets of synthetic identities as a method of dataset anonymisation. Many researchers have also attempted to use GAN-generated data to augment training datasets with varying degrees of success [16,29,35].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Assessment of GANs for Identity-related Applications

Marriott¹,

Madiouni²,

Romdhani³

et al. 2020

2020 IEEE International Joint Conference on Biometrics (IJCB)

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) are now capable of producing synthetic face images of exceptionally high visual quality. In parallel to the development of GANs themselves, efforts have been made to develop metrics to objectively assess the characteristics of the synthetic images, mainly focusing on visual quality and the variety of images. Little work has been done, however, to assess overfitting of GANs and their ability to generate new identities. In this paper we apply a state of the art biometric network to various datasets of synthetic images and perform a thorough assessment of their identity-related characteristics. We conclude that GANs can indeed be used to generate new, imagined identities meaning that applications such as anonymisation of image sets and augmentation of training datasets with distractor images are viable applications. We also assess the ability of GANs to disentangle identity from other image characteristics and propose a novel GAN triplet loss that we show to improve this disentanglement.

show abstract

“…There have been also some works to synthesize face images to be used as synthetic training data for face recognition methods either by directly using GAN-generated images [38] or by controlling pose-space with a conditional-GAN [39], [40], [41]. [42] propose many augmentation techniques, such as rotating, changing expression and shape, based on 3DMMs.…”

Section: Boosting Face Recognition By Synthetic Training Datamentioning

confidence: 99%

Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks

Gecer,

Lattas,

Ploumpis

et al. 2019

Preprint

View full text Add to dashboard Cite

Generating realistic 3D faces is of high importance for computer graphics and computer vision applications. Generally, research on 3D face generation revolves around linear statistical models of the facial surface. Nevertheless, these models cannot represent faithfully either the facial texture or the normals of the face, which are very crucial for photo-realistic face synthesis. Recently, it was demonstrated that Generative Adversarial Networks (GANs) can be used for generating high-quality textures of faces. Nevertheless, the generation process either omits the geometry and normals, or independent processes are used to produce 3D shape information. In this paper, we present the first methodology that generates high-quality texture, shape, and normals jointly, which can be used for photo-realistic synthesis. To do so, we propose a novel GAN that can generate data from different modalities while exploiting their correlations. Furthermore, we demonstrate how we can condition the generation on the expression and create faces with various facial expressions. The qualitative results shown in this pre-print is compressed due to size limitations, full resolution results and the accompanying video can be found at the project page: https://github.com/barisgecer/TBGAN.

show abstract

Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy

Cited by 4 publications

References 52 publications

On the use of automatically generated synthetic image datasets for benchmarking face recognition

On the use of automatically generated synthetic image datasets for benchmarking face recognition

An Assessment of GANs for Identity-related Applications

Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks

Contact Info

Product

Resources

About