# A Deep Drift-Diffusion Model for Image Aesthetic Score Distribution Prediction

arXiv: https://arxiv.org/abs/2010.07661 · HTML: https://mlsanity.com/paper/2010.07661/

## Key facts

- Cited by 1 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 9 of its 30 references that are in the map.
- First posted on arXiv 15 Oct 2020.

## 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, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Photo Aesthetics Ranking Network with Attributes and Content Adaptation](https://mlsanity.com/paper/1606.01621/) (2016)
- [Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks](https://mlsanity.com/paper/1611.05916/) (2016)
- [Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment](https://mlsanity.com/paper/2004.03015/) (2020)
- [Composition-Aware Image Aesthetics Assessment](https://mlsanity.com/paper/1907.10801/) (2019)
- [A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction](https://mlsanity.com/paper/1812.07989/) (2018)
- [Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence](https://mlsanity.com/paper/1708.07089/) (2017)
- [Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs](https://mlsanity.com/paper/1908.01308/) (2019)

## Built on by (most cited first, 1 of 1)

- [Parameterized Image Quality Score Distribution Prediction](https://mlsanity.com/paper/2203.00926/) (2022)

## Abstract (arXiv)

The task of aesthetic quality assessment is complicated due to its subjectivity. In recent years, the target representation of image aesthetic quality has changed from a one-dimensional binary classification label or numerical score to a multi-dimensional score distribution. According to current methods, the ground truth score distributions are straightforwardly regressed. However, the subjectivity of aesthetics is not taken into account, that is to say, the psychological processes of human beings are not taken into consideration, which limits the performance of the task. In this paper, we propose a Deep Drift-Diffusion (DDD) model inspired by psychologists to predict aesthetic score distribution from images. The DDD model can describe the psychological process of aesthetic perception instead of traditional modeling of the results of assessment. We use deep convolution neural networks to regress the parameters of the drift-diffusion model. The experimental results in large scale aesthetic image datasets reveal that our novel DDD model is simple but efficient, which outperforms the state-of-the-art methods in aesthetic score distribution prediction. Besides, different psychological processes can also be predicted by our model.