Age Progression/Regression by Conditional Adversarial Autoencoder

By Zhifei Zhang, Yang Song, Hairong Qi. 2017

1,319 citations recorded by the source corpus.

If I provide you a face image of mine (without telling you the actual age when I took the picture) and a large amount of face images that I crawled (containing labeled faces of different ages but not necessarily paired), can you show me what I would look like when I am 80 or what I was like when I was 5? The answer is probably a No. Most existing face aging works attempt to learn the transformation between age groups and thus would require the paired samples as well as the labeled query image. In this paper, we look at the problem from a generative modeling perspective such that no paired samples is required. In addition, given an unlabeled image, the generative model can directly produce the image with desired age attribute. We propose a conditional adversarial autoencoder (CAAE) that learns a face manifold, traversing on which smooth age progression and regression can be realized simultaneously. In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator. The latent vector preserves personalized face features (i.e., personality) and the age condition controls progression vs. regression. Two adversarial networks are imposed on the encoder and generator, respectively, forcing to generate more photo-realistic faces. Experimental results demonstrate the appealing performance and flexibility of the proposed framework by comparing with the state-of-the-art and ground truth.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, methodology): “Some datasets were collected via web search using keywords such as “Asian boy” [75].”
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2017, background): “Compared to L1 loss, which often leads to blurry images [21, 22], the adversarial loss [16] has become a popular choice for many image-to-image tasks [10, 24, 25, 31, 40, 45, 53, 58, 64].”
StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation (2017, background): “Generative adversarial networks (GANs) [3] have shown remarkable results in various computer vision tasks such as image generation [1, 6, 23, 31], image translation [7, 8, 32], super-resolution imaging [13], and face image synthesis [9, 15, 25, 30].”
A Step Toward More Inclusive People Annotations for Fairness (2021, background): “, Celeb-A [18], FairFace [14], UTKFace [32]) but may also be useful for studying bias [1, 23].”
Differential Privacy Has Disparate Impact on Model Accuracy (2019, methodology): “We use the recently released Flickr-based Diversity in Faces (DiF) dataset [27] and the UTKFace dataset [39] as another source of darker-skinned faces.”
Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, background): “face frontal view generation [50], generating new human poses [51], photos to emojis [52], photograph editing [53]–[55], face aging [56], [57], photo blending [58], super resolution [59]–[61], photo inpainting [62]–[64], video prediction [65], and 3D object generation [66], [67]; among”
Diversity in Faces (2019, methodology): “The gender annotations used two class labels (male and female) and the age group labeling used seven classes ([0-3],[4-12],[13-19],[20-30],[31-45],[46-60],[61-]), as well as a continuous age value to be consistent with the automatic prediction labels.”
Transferring GANs: generating images from limited data (2018, methodology): “GANs have further been widely applied in applications, including super-resolution [26], 3D object generation and reconstruction [40], human pose estimation [28], and age estimation [47].”
Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels (2019, methodology): “Table 1: Age regression and gender classification results on UTKFace [35] with (a) the full and (b) limited training set.”
Geometry-Contrastive GAN for Facial Expression Transfer. (2018, background): “Conditional GANs (cGANs) have also been widely applied in many face-related tasks, such as face pose manipulation [29], face aging [32], and facial expression transfer [3, 6, 22, 33].”
Only a matter of style: age transformation using a style-based regression model (2021, methodology): “To model age transformation as an image-to-image problem, most works [Antipov et al. 2017; He et al. 2019; Or-El et al. 2020; Tang et al. 2018; Wang et al. 2016; Yang et al. 2019; Zhang et al. 2017] use ageannotated data and learn amapping between pre-defined age groups.”
Applications of Generative Adversarial Networks (GANs): An Updated Review (2019, background): “Face age progression (i.e., prediction of future looks) and regression (i.e., estimation of previous looks), also referred to as face aging and rejuvenation, aims to render face images with or without the “aging” effect but still preserve personalized features of the face (i.e., personality) [140].”
Mitigating Bias in Gender, Age and Ethnicity Classification: A Multi-task Convolution Neural Network Approach (2018, neutral): “[25], consisting of all required labeling.”
A de novo molecular generation method using latent vector based generative adversarial network (2019, methodology): “In other application areas, Conditional AAEs with similar training schemes have been applied to manipulate images of faces [50].”
StyleGAN2 Distillation for Feed-forward Image Manipulation (2020, background): “Face aging/rejuvenation is a special task which gets a lot of attention [60,50,19].”
Generative Adversarial Networks (GANs) (2020, background): “Generation of realistic images has wide range of practical applications, such as anime character generation [159]–[164], image synthesis [165]–[168], super resolution [10], [124], [169]–[177], image editing and blending [178], [179], inpainting [125], [180]–[182], interactive image generation [183],”
A survey on face data augmentation for the training of deep neural networks (2019, background): “But such models typically suffer from high complexity and computational cost [68].”
A Generative Model of Worldwide Facial Appearance (2019, methodology): “Recently, several methods have been proposed for transferring fine-grained attributes such as age [23, 47] or transient attributes, such as facial hair and hair color [29, 45].”