# Exploring CNN-based models for image's aesthetic score prediction with using ensemble

arXiv: https://arxiv.org/abs/2210.05119 · HTML: https://mlsanity.com/paper/2210.05119/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 12 of 12)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Effective Aesthetics Prediction with Multi-level Spatially Pooled Features](https://mlsanity.com/paper/1904.01382/) (2019)
- [Image Aesthetic Assessment: An Experimental Survey](https://mlsanity.com/paper/1610.00838/) (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)
- [Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning](https://mlsanity.com/paper/1911.11419/) (2019)
- [CNN-based Repetitive self-revised learning for photos' aesthetics imbalanced classification](https://mlsanity.com/paper/2003.03081/) (2020)
- [Assessing aesthetics of generated abstract images using correlation structure](https://mlsanity.com/paper/2105.08635/) (2021)
- [Exploring to establish an appropriate model for image aesthetic assessment via CNN-based RSRL: An empirical study](https://mlsanity.com/paper/2106.03316/) (2021)
- [Learning Image Aesthetic Assessment from Object-level Visual Components](https://mlsanity.com/paper/2104.01548/) (2021)

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

- [TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs](https://mlsanity.com/paper/2505.19535/) (2025)

## Abstract (arXiv)

In this paper, we proposed a framework of constructing two types of the automatic image aesthetics assessment models with different CNN architectures and improving the performance of the image's aesthetic score prediction by the ensemble. Moreover, the attention regions of the models to the images are extracted to analyze the consistency with the subjects in the images. The experimental results verify that the proposed method is effective for improving the AS prediction. Moreover, it is found that the AS classification models trained on XiheAA dataset seem to learn the latent photography principles, although it can't be said that they learn the aesthetic sense.