# Generative Pre-training for Subjective Tasks: A Diffusion Transformer-Based Framework for Facial Beauty Prediction

arXiv: https://arxiv.org/abs/2507.20363 · HTML: https://mlsanity.com/paper/2507.20363/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction](https://mlsanity.com/paper/1801.06345/) (2018)
- [Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2203.01536/) (2022)
- [SCUT-FBP: A Benchmark Dataset for Facial Beauty Perception](https://mlsanity.com/paper/1511.02459/) (2015)
- [Label distribution based facial attractiveness computation by deep residual learning](https://mlsanity.com/paper/1609.00496/) (2016)

## Built on by (most cited first, 4 of 4)

- [Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction](https://mlsanity.com/paper/2509.05078/) (2025)
- [SynergyNet: Fusing Generative Priors and State-Space Models for Facial Beauty Prediction](https://mlsanity.com/paper/2509.17172/) (2025)
- [FairViT-GAN: A Hybrid Vision Transformer with Adversarial Debiasing for Fair and Explainable Facial Beauty Prediction](https://mlsanity.com/paper/2509.23859/) (2025)
- [VM-BeautyNet: A Synergistic Ensemble of Vision Transformer and Mamba for Facial Beauty Prediction](https://mlsanity.com/paper/2510.16220/) (2025)

## Abstract (arXiv)

Facial Beauty Prediction (FBP) is a challenging computer vision task due to its subjective nature and the subtle, holistic features that influence human perception. Prevailing methods, often based on deep convolutional networks or standard Vision Transformers pre-trained on generic object classification (e.g., ImageNet), struggle to learn feature representations that are truly aligned with high-level aesthetic assessment. In this paper, we propose a novel two-stage framework that leverages the power of generative models to create a superior, domain-specific feature extractor. In the first stage, we pre-train a Diffusion Transformer on a large-scale, unlabeled facial dataset (FFHQ) through a self-supervised denoising task. This process forces the model to learn the fundamental data distribution of human faces, capturing nuanced details and structural priors essential for aesthetic evaluation. In the second stage, the pre-trained and frozen encoder of our Diffusion Transformer is used as a backbone feature extractor, with only a lightweight regression head being fine-tuned on the target FBP dataset (FBP5500). Our method, termed Diff-FBP, sets a new state-of-the-art on the FBP5500 benchmark, achieving a Pearson Correlation Coefficient (PCC) of 0.932, significantly outperforming prior art based on general-purpose pre-training. Extensive ablation studies validate that our generative pre-training strategy is the key contributor to this performance leap, creating feature representations that are more semantically potent for subjective visual tasks.