Lifespan Age Transformation Synthesis

Or-El, Roy; Sengupta, Shamik; Fried, Ohad; Shechtman, Eli; Kemelmacher-Shlizerman, Ira

doi:10.1007/978-3-030-58539-6_44

Cited by 89 publications

(99 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it becomes more challenging once FAP is conducted as lifespan ageing since the generative network must learn more complex ageing patterns. In this context, Or-El et al [25] proposed a lifespan FAP method based on a multi-domain imageto-image conditional GAN framework. Instead of defining Additional discriminator to distinguish between real and synthesized images of adjacent age groups.…”

Section: Referencementioning

confidence: 99%

“…Fang et al [46] 2020 Age group transitions CACD, MORPH-II, CALFW cGAN with triple-translation loss. Ning et al [92] 2020 Age group transitions CACD, private DB (Webcrawled) Or-El et al [25] 2020 Continuous ageing FFHQ-ageing Enables continuous ageing by interpolating between discrete age groups. Pham et al [93] 2020 Age group transitions UTKFace, FG-NET Sheng et al [94] 2020 Age group transitions CACD cGANs with rank-based discriminators [95].…”

Section: Referencementioning

confidence: 99%

“…In addition to the above described evaluation techniques, Figure 7 provides an impression on the results of three recently published FAP methods with publicly available implementations [26], [25], [102]. Following the evaluation techniques presented in this section, all images are annotated with FIDs and CSs.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…Other than the previous FAP approaches, the method by Or-El et al [25] operates in a lower resolution of 256x256 pixels. The face images are preprocessed by replacing the noisy background with a plain grey colour to support the generator to focus on the age-synthesis of the face region only.…”

Section: Performance Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

Deep Face Age Progression: A Survey

2021

View full text Add to dashboard Cite

Face Age Progression (FAP) refers to synthesizing face images while simulating ageing effects, thus enabling predicting the future appearance of an individual. The generation of age-progressed face images brings benefits for various applications, ranging from face recognition systems to forensic investigations and digital entertainment. In particular, the recent success achieved with deep generative networks significantly leveraged the quality of age-synthesized face images in terms of visual fidelity, ageing accuracy and identity preservation. However, the high number of contributions in recent years requires systematically structuring new findings and ideas to identify a common taxonomy, accelerate future research and reduce redundancy. Therefore, we present a comparative analysis of recent deep learning based face age progression methods for both adult and child-based face ageing, broken down into three high-level concepts: translation-based, condition-based, and sequence-based FAP. Further, we offer a comprehensive summary of the most common performance evaluation techniques, cross-age datasets, and open challenges to steer future research in the right direction.

show abstract

Section: Referencementioning

confidence: 99%

Section: Referencementioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Deep Face Age Progression: A Survey

2021

View full text Add to dashboard Cite

show abstract

“…For example, the same facial texture can be reposed with 3D models to add more variation in facial pose and shape [6,7]. GAN-based models have also been successfully deployed to generate hires synthetic face images [8] or edit visual attributes like age [9], lighting and pose [10], gender and expressions [11].…”

Section: Introductionmentioning

confidence: 99%

Synthesize & Learn: Jointly Optimizing Generative and Classifier Networks for Improved Drowsiness Detection

Banerjee

Joshi

Ghoneim

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Driving in a state of drowsiness is a major cause of road accidents, resulting in tremendous damage to life and property. Developing robust, automatic, real-time systems that can infer drowsiness states of drivers has the potential of making lifesaving impact. However, real-world drowsy driving datasets are unbalanced, due to the sparsity of drowsy driving events. We focus on the problem of alleviating the class imbalance problem by using generative adversarial networks (GAN) to synthesize examples of sparse classes directly in the featurespace. Our GAN-based framework simultaneously generates realistic examples of sparse classes while using the generated samples to improve the performance of a separate drowsiness classifier. We validate this approach in a real-world drowsiness dataset, where we demonstrate a classifier trained using this approach outperforms a stand-alone classifier trained without any GAN-based augmentations.

show abstract

High‐resolution knee plain radiography image synthesis using style generative adversarial network adaptive discriminator augmentation

Ahn

Choi

et al. 2022

Journal Orthopaedic Research

View full text Add to dashboard Cite

In this retrospective study, 10,000 anteroposterior (AP) radiography of the knee from a single institution was used to create medical data set that are more balanced and cheaper to create. Two types of convolutional networks were used, deep convolutional GAN (DCGAN) and Style GAN Adaptive Discriminator Augmentation (StyleGAN2-ADA). To verify the quality of generated images from StyleGAN2-ADA compared to real ones, the Visual Turing test was conducted by two computer vision experts, two orthopedic surgeons, and a musculoskeletal radiologist. For quantitative analysis, the Fréchet inception distance (FID), and principal component analysis (PCA) were used. Generated images reproduced the features of osteophytes, joint space narrowing, and sclerosis. Classification accuracy of the experts was 34%, 43%, 44%, 57%, and 50%. FID between the generated images and real ones was 2.96, which is significantly smaller than another medical data set (BreCaHAD = 15.1). PCA showed that no significant difference existed between the PCs of the real and generated images (p > 0.05). At least 2000 images were required to make reliable images optimally. By performing PCA in latent space, we were able to control the desired PC that show a progression of arthritis. Using a GAN, we were able to generate knee X-ray images that accurately reflected the characteristics of the arthritis progression stage, which neither human experts nor artificial intelligence could discern apart from the real images. In summary, our research opens up the potential to adopt a generative model to synthesize realistic anonymous images that can also solve data scarcity and class inequalities.

show abstract

Lifespan Age Transformation Synthesis

Cited by 89 publications

References 42 publications

Deep Face Age Progression: A Survey

Deep Face Age Progression: A Survey

Synthesize & Learn: Jointly Optimizing Generative and Classifier Networks for Improved Drowsiness Detection

High‐resolution knee plain radiography image synthesis using style generative adversarial network adaptive discriminator augmentation

Contact Info

Product

Resources

About