Age Progression/Regression by Conditional Adversarial Autoencoder

Abstract

"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.

Accepted by The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• DRAW: A Recurrent Neural Network For Image Generation
• Energy-based Generative Adversarial Network
• Autoencoding beyond pixels using a learned similarity metric
• Adversarial Autoencoders
• Personalized Age Progression with Aging Dictionary

Cited by in corpus (34)

• Overlearning Reveals Sensitive Attributes
• Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
• Geometry-Contrastive GAN for Facial Expression Transfer
• Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
• Only a Matter of Style: Age Transformation Using a Style-Based Regression Model
• Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder
• Robust Cross-View Gait Recognition with Evidence: A Discriminant Gait GAN (DiGGAN) Approach
• Facial Aging and Rejuvenation by Conditional Multi-Adversarial Autoencoder with Ordinal Regression
• Global and Local Consistent Age Generative Adversarial Networks
• A Utility-Preserving GAN for Face Obscuration
• What Will Your Child Look Like? DNA-Net: Age and Gender Aware Kin Face Synthesizer
• Finding Missing Children: Aging Deep Face Features
• CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation
• Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
• Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
• Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
• Learning Compositional Visual Concepts with Mutual Consistency
• All-In-One: Facial Expression Transfer, Editing and Recognition Using A Single Network
• Decoupled Learning for Conditional Adversarial Networks
• Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!
• r-BTN: Cross-domain Face Composite and Synthesis from Limited Facial Patches
• A Personalized Affective Memory Neural Model for Improving Emotion Recognition
• Class-Distinct and Class-Mutual Image Generation with GANs
• Longitudinal Face Aging in the Wild - Recent Deep Learning Approaches
• Face Aging with Contextual Generative Adversarial Nets
• Controllable Face Aging
• PortraitGAN for Flexible Portrait Manipulation
• Facial Analysis Systems and Down Syndrome
• Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
• High Diversity Attribute Guided Face Generation with GANs
• Latent Transformations for Object View Points Synthesis
• Slice Tuner: A Selective Data Acquisition Framework for Accurate and Fair Machine Learning Models
• Shape-conditioned Image Generation by Learning Latent Appearance Representation from Unpaired Data