# Synthetic Data Generation for Emotional Depth Faces: Optimizing Conditional DCGANs via Genetic Algorithms in the Latent Space and Stabilizing Training with Knowledge Distillation

arXiv: https://arxiv.org/abs/2508.09188 · HTML: https://mlsanity.com/paper/2508.09188/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 20 of its 60 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 20 of 20)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Comprehensive Exploration of Synthetic Data Generation: A Survey](https://mlsanity.com/paper/2401.02524/) (2024)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Example-based Motion Synthesis via Generative Motion Matching](https://mlsanity.com/paper/2306.00378/) (2023)
- [4D Facial Expression Diffusion Model](https://mlsanity.com/paper/2303.16611/) (2023)
- [Kernel density estimation based sampling for imbalanced class distribution](https://mlsanity.com/paper/1910.07842/) (2019)
- [Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder](https://mlsanity.com/paper/1708.09126/) (2017)
- [Joint Deep Learning of Facial Expression Synthesis and Recognition](https://mlsanity.com/paper/2002.02194/) (2020)
- [SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data](https://mlsanity.com/paper/2410.09865/) (2024)
- [3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning](https://mlsanity.com/paper/2009.14798/) (2020)
- [CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer](https://mlsanity.com/paper/2111.15159/) (2021)
- [Synthetic Data Generation by Supervised Neural Gas Network for Physiological Emotion Recognition Data](https://mlsanity.com/paper/2501.16353/) (2025)
- [High-Accuracy Facial Depth Models derived from 3D Synthetic Data](https://mlsanity.com/paper/2003.06211/) (2020)
- [Altering Facial Expression Based on Textual Emotion](https://mlsanity.com/paper/2112.01454/) (2021)
- [Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition](https://mlsanity.com/paper/2503.14513/) (2025)
- [An augmentation strategy to mimic multi-scanner variability in MRI](https://mlsanity.com/paper/2103.12595/) (2021)
- [Victoria Amazonica Optimization (VAO): An Algorithm Inspired by the Giant Water Lily Plant](https://mlsanity.com/paper/2303.08070/) (2023)

## Abstract (arXiv)

Affective computing faces a major challenge: the lack of high-quality, diverse depth facial datasets for recognizing subtle emotional expressions. We propose a framework for synthetic depth face generation using an optimized GAN with Knowledge Distillation (EMA teacher models) to stabilize training, improve quality, and prevent mode collapse. We also apply Genetic Algorithms to evolve GAN latent vectors based on image statistics, boosting diversity and visual quality for target emotions. The approach outperforms GAN, VAE, GMM, and KDE in both diversity and quality. For classification, we extract and concatenate LBP, HOG, Sobel edge, and intensity histogram features, achieving 94% and 96% accuracy with XGBoost. Evaluation using FID, IS, SSIM, and PSNR shows consistent improvement over state-of-the-art methods.