Continuous Face Aging via Self-estimated Residual Age Embedding

@article{Li2021ContinuousFA,
  title={Continuous Face Aging via Self-estimated Residual Age Embedding},
  author={Zeqi Li and Ruowei Jiang and Parham Aarabi},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={15003-15012}
}
  • Zeqi Li, R. Jiang, Parham Aarabi
  • Published 30 April 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Face synthesis, including face aging, in particular, has been one of the major topics that witnessed a substantial improvement in image fidelity by using generative adversarial networks (GANs). Most existing face aging approaches divide the dataset into several age groups and leverage group-based training strategies, which lacks the ability to provide fine-controlled continuous aging synthesis in nature. In this work, we propose a unified network structure that embeds a linear age estimator… 
1 Citations
Interpretable Generative Adversarial Networks
TLDR
This paper proposes a generic method to modify a traditional GAN into an interpretable GAN, which ensures that filters in an intermediate layer of the generator encode disentangled localized visual concepts.

References

SHOWING 1-10 OF 54 REFERENCES
Lifespan Age Transformation Synthesis
TLDR
This work proposes a novel multi-domain image-to-image generative adversarial network architecture, whose learned latent space models a continuous bi-directional aging process.
S2GAN: Share Aging Factors Across Ages and Share Aging Trends Among Individuals
TLDR
The proposed method can achieve continuous face aging with favorable aging accuracy, identity preservation, and fidelity, and befitted from the effective design, a unique model is capable of all ages and the prediction time is significantly saved.
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
TLDR
This work proposes a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions and introduces the "Frechet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score.
Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval
TLDR
A novel coding framework called Cross-Age Reference Coding (CARC), which is able to encode the low-level feature of a face image with an age-invariant reference space and can achieve state-of-the-art performance on both the dataset and other widely used dataset for face recognition across age, MORPH dataset.
Mean-Variance Loss for Deep Age Estimation from a Face
TLDR
A new loss function, called mean-variance loss, is proposed for robust age estimation via distribution learning, which penalizes difference between the mean and variance of the estimated age distribution and the ground-truth age.
Face Aging with Identity-Preserved Conditional Generative Adversarial Networks
TLDR
An Identity-Preserved Conditional Generative Adversarial Networks (IPCGANs) framework is proposed, in which an identity-preserved module preserves the identity information and an age classifier forces the generated face with the target age.
Learning Face Age Progression: A Pyramid Architecture of GANs
TLDR
A novel generative adversarial network based approach that separately models the constraints for the intrinsic subject-specific characteristics and the age-specific facial changes with respect to the elapsed time, ensuring that the generated faces present desired aging effects while simultaneously keeping personalized properties stable.
Age Progression/Regression by Conditional Adversarial Autoencoder
TLDR
A conditional adversarial autoencoder that learns a face manifold, traversing on which smooth age progression and regression can be realized simultaneously is proposed, and the appealing performance and flexibility of the proposed framework is demonstrated by comparing with the state-of-the-art and ground truth.
DEX: Deep EXpectation of Apparent Age from a Single Image
TLDR
The proposed method, Deep EXpectation (DEX) of apparent age, first detects the face in the test image and then extracts the CNN predictions from an ensemble of 20 networks on the cropped face, significantly outperforming the human reference.
Generative adversarial networks
  • Advances in neural information processing systems,
  • 2014
...
...