# Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning

arXiv: https://arxiv.org/abs/1911.11419 · HTML: https://mlsanity.com/paper/1911.11419/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 7 of 7)

- [Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method](https://mlsanity.com/paper/2303.15166/) (2023)
- [A Hypothesis for the Aesthetic Appreciation in Neural Networks](https://mlsanity.com/paper/2108.02646/) (2021)
- [Automatic Generation of Product-Image Sequence in E-commerce](https://mlsanity.com/paper/2206.12994/) (2022)
- [Modeling, Quantifying, and Predicting Subjectivity of Image Aesthetics](https://mlsanity.com/paper/2208.09666/) (2022)
- [Exploring CNN-based models for image's aesthetic score prediction with using ensemble](https://mlsanity.com/paper/2210.05119/) (2022)
- [Product Review Image Ranking for Fashion E-commerce](https://mlsanity.com/paper/2308.05390/) (2023)
- [How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space](https://mlsanity.com/paper/2608.27121/) (2026)

## Abstract (arXiv)

Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both aesthetic labels and related image attributes. In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective. Our motivation is that a suitable feature representation for image aesthetic assessment should be able to distinguish different expert-designed image manipulations, which have close relationships with negative aesthetic effects. To this end, we design two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances. The features from our pretext tasks are then adapted for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification. We conduct extensive quantitative experiments on three benchmark datasets and demonstrate that our approach can faithfully extract aesthetics-aware features and outperform alternative pretext schemes. Moreover, we achieve comparable results to state-of-the-art supervised methods that use 10 million labels from ImageNet.