Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks

Liu, Yunfan; Li, Qi; Sun, Zhenan

doi:10.1109/cvpr.2019.01215

Cited by 140 publications

(139 citation statements)

References 27 publications

Supporting

Mentioning

139

Contrasting

Order By: Relevance

“…Regarding the application challenges and opportunities in deep FAM, facial makeup [65,10,7] and aging [109,81,69] have become hot topics in computer vision. The two tasks focus more on subtle facial details related to makeup and age attributes.…”

Section: Model-based Methodsmentioning

confidence: 99%

“…Face makeup [65,10,7] and face aging [109,81,69] are two hot topics in deep FAM related applications. They have played important roles in mobile device entertainment (e.g., beauty cameras) and identity-relevant face verification.…”

Section: Applicationsmentioning

confidence: 99%

“…Hence, this task can not only be applied to digital entertainment but also provide support to social safety, such as fugitive researches and cross-age identity verification. The most crucial issue in face aging is that there are no sufficient paired images for the same person at different ages [69]. Recently, the development of deep learning has lead face makeup and face aging to promising results, and they have become important research branches independent of general deep FAM methods.…”

Section: Applicationsmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Deep Facial Attribute Analysis

et al. 2020

View full text Add to dashboard Cite

Facial attribute analysis has received considerable attention when deep learning techniques made remarkable breakthroughs in this field over the past few years. Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes. In this paper, we provide a comprehensive survey of deep facial attribute analysis from the perspectives of both estimation and manipulation.First, we summarize a general pipeline that deep facial attribute analysis follows, which comprises two stages: data preprocessing and model construction. Additionally, we introduce the underlying theories of this twostage pipeline for both FAE and FAM. Second, the datasets and performance metrics commonly used in facial attribute analysis are presented. Third, we create a taxonomy of state-of-the-art methods and review deep FAE and FAM algorithms in detail. Furthermore, several additional facial attribute related issues are introduced, as well as relevant real-world applications. Finally, we discuss possible challenges and promising future research directions.

show abstract

Section: Model-based Methodsmentioning

confidence: 99%

Section: Applicationsmentioning

confidence: 99%

Section: Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Deep Facial Attribute Analysis

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To avoid the suspicion that the limited images demonstrated in the paper, we have also evaluated all results quantitatively. In literature [5,6], there are two critical evaluation metrics in age progression, i.e. identity permanence and aging accuracy.…”

Section: Quantitative Comparisonmentioning

confidence: 99%

“…In recent years, face aging has attracted major attention due to its extensive use in numerous applications, entertainment [1], finding missing children [2], cross-age face recognition [3], etc. Although impressive results have been achieved recently [4,5,6,7,8], there are still many challenges due to the intrinsic complexity of aging in nature and the insufficient labeled aging data. Intuitively, the generated face images should be photo-realistic, e.g., without serious ghosting artifacts.…”

Section: Introductionmentioning

confidence: 99%

Look Globally, Age Locally: Face Aging With an Attention Mechanism

Zhu

Huang

Shan

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Face aging is of great importance for cross-age recognition and entertainment-related applications. Recently, conditional generative adversarial networks (cGANs) have achieved impressive results for face aging. Existing cGANs-based methods usually require a pixel-wise loss to keep the identity and background consistent. However, minimizing the pixel-wise loss between the input and synthesized images likely resulting in a ghosted or blurry face. To address this deficiency, this paper introduces an Attention Conditional GANs (AcGANs) approach for face aging, which utilizes attention mechanism to only alert the regions relevant to face aging. In doing so, the synthesized face can well preserve the background information and personal identity without using the pixel-wise loss, and the ghost artifacts and blurriness can be significantly reduced. Based on the benchmarked dataset Morph, both qualitative and quantitative experiment results demonstrate superior performance over existing algorithms in terms of image quality, personal identity, and age accuracy.

show abstract

Toward feature space adversarial attack in the frequency domain

Wang

Tan

Haoran

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Recent researchers have shown that deep neural networks (DNNs) are vulnerable to adversarial exemplars, making them unsuitable for security‐critical applications. Transferability of adversarial examples is crucial for attacking black‐box models, which facilitates adversarial attacks in more practical scenarios. We propose a novel adversarial attack with high transferability. Unlike existing attacks that directly modify the input pixels, our attack is executed in the feature space. More specifically, we corrupt the abstract features by maximizing the feature distance between the adversarial example and clean images with a perceptual similarity network, inducing model misclassification. In addition, we apply a spectral transformation to the input, thus narrowing the search space in the frequency domain to enhance the transferability of adversarial examples. The disruption of crucial features in a specific frequency component achieves greater transferability. Extensive evaluations illustrate that our approach is easily compatible with many existing frameworks for transfer attacks and can significantly improve the baseline performance of black‐box attacks. Moreover, we can obtain a higher fooling rate even if the model has a defense technique. We achieve a maximum black‐box fooling rate of 61.70% on the defense model. Our work indicates that existing pixel space defense techniques are difficult to guarantee the robustness of the feature space, and the feature space from a frequency perspective is promising for developing more robust models.

show abstract

Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks

Cited by 140 publications

References 27 publications

A Survey of Deep Facial Attribute Analysis

A Survey of Deep Facial Attribute Analysis

Look Globally, Age Locally: Face Aging With an Attention Mechanism

Toward feature space adversarial attack in the frequency domain

Contact Info

Product

Resources

About