# Age Progression and Regression with Spatial Attention Modules

arXiv: https://arxiv.org/abs/1903.02133 · HTML: https://mlsanity.com/paper/1903.02133/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2019.

## Built on by (most cited first, 8 of 8)

- [When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework](https://mlsanity.com/paper/2103.01520/) (2021)
- [When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark](https://mlsanity.com/paper/2210.09835/) (2022)
- [TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation](https://mlsanity.com/paper/2305.08779/) (2023)
- [Learning Position-Aware Implicit Neural Network for Real-World Face Inpainting](https://mlsanity.com/paper/2401.10537/) (2024)
- [AgeFlow: Conditional Age Progression and Regression with Normalizing Flows](https://mlsanity.com/paper/2105.07239/) (2021)
- [RoutingGAN: Routing Age Progression and Regression with Disentangled Learning](https://mlsanity.com/paper/2102.00601/) (2021)
- [A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks](https://mlsanity.com/paper/2109.07373/) (2021)
- [Overcoming Occlusions in the Wild: A Multi-Task Age Head Approach to Age Estimation](https://mlsanity.com/paper/2506.13445/) (2025)

## Abstract (arXiv)

Age progression and regression refers to aesthetically render-ing a given face image to present effects of face aging and rejuvenation, respectively. Although numerous studies have been conducted in this topic, there are two major problems: 1) multiple models are usually trained to simulate different age mappings, and 2) the photo-realism of generated face images is heavily influenced by the variation of training images in terms of pose, illumination, and background. To address these issues, in this paper, we propose a framework based on conditional Generative Adversarial Networks (cGANs) to achieve age progression and regression simultaneously. Particularly, since face aging and rejuvenation are largely different in terms of image translation patterns, we model these two processes using two separate generators, each dedicated to one age changing process. In addition, we exploit spatial attention mechanisms to limit image modifications to regions closely related to age changes, so that images with high visual fidelity could be synthesized for in-the-wild cases. Experiments on multiple datasets demonstrate the ability of our model in synthesizing lifelike face images at desired ages with personalized features well preserved, and keeping age-irrelevant regions unchanged.