Learning from Longitudinal Face Demonstration—Where Tractable Deep Modeling Meets Inverse Reinforcement Learning

Abstract

This paper presents a novel Subject-dependent Deep Aging Path (SDAP), which inherits the merits of both Generative Probabilistic Modeling and Inverse Reinforcement Learning to model the facial structures and the longitudinal face aging process of a given subject. The proposed SDAP is optimized using tractable log-likelihood objective functions with Convolutional Neural Networks (CNNs) based deep feature extraction. Instead of applying a fixed aging development path for all input faces and subjects, SDAP is able to provide the most appropriate aging development path for individual subject that optimizes the reward aging formulation. Unlike previous methods that can take only one image as the input, SDAP further allows multiple images as inputs, i.e. all information of a subject at either the same or different ages, to produce the optimal aging path for the given subject. Finally, SDAP allows efficiently synthesizing in-thewild aging faces. The proposed model is experimented in both tasks of face aging synthesis and cross-age face verification. The experimental results consistently show SDAP achieves the state-of-the-art performance on numerous face aging databases, i.e. FG-NET, MORPH, AginG Faces in the Wild (AGFW), and Cross-Age Celebrity Dataset (CACD). Furthermore, we also evaluate the performance of SDAP on large-scale Megaface challenge to demonstrate the advantages of the proposed solution.

Global and Local Consistent Age Generative Adversarial Networks

“…However, due to the extreme challenges involving diverse genetics and living styles, rigid requirement for training datasets and large variation in illumination, age progression/regression is still a challenging task. In prior works, direct and step-by-step aging synthesis are mainly used for age progression/regression [2]. In direct aging synthesis, target age faces can be directly synthesized utilizing the relationships between input faces and their corresponding target age labels.…”

Recent Generative Adversarial Approach in Face Aging and Dataset Review

“…Additional aging controller used in TNVP structure at research by [7], based on the hypothesis that each individual has their facial development. Rather than simply embedding aging transformations into pairs that are linked between successive age groups, the Subject Dependent Aging Policy(SDAP) structure studies age transformations within the entire facial sequence to produce better synthetic ages.…”

“…Deep learning algorithms have a better ability to interpret and transfer non-linear aging features. Several faces aging studies on how to produce superior synthetic image results as in [2][3][4] [5][6] [7], including the Generative Adversarial Networks method.…”

Enhance Portable Radiograph for Fast and High Accurate COVID-19 Monitoring

“…The discriminator D P , and D C encourage the transferred images and the real images to be similar, as given in Figure 3a. Flow-based generative models [19][20][21] are a class of latent variable generative models that clearly identify the generator as an invertible mapping h : Z → P between a set of latent variables Z and a set of observed variables P. Let p P and p Z indicate the marginal densities given by the model over P and Z, respectively. Using the change-of-variables formula, these marginal densities are defined as…”