# Personalised aesthetics with residual adapters

## TL;DR

This paper introduces a residual learning model that personalizes aesthetic evaluation in photography, capturing individual preferences efficiently while outperforming existing methods and enabling applications in enhancement and recommendation systems.

## Contribution

The proposed residual adapter model uniquely learns user-specific aesthetic preferences with limited parameters, surpassing state-of-the-art accuracy and supporting content-based and hybrid recommender systems.

## Key findings

- Outperforms existing aesthetic prediction models
- Efficiently learns user preferences with few parameters
- Applicable to picture enhancement and recommendation systems

## Abstract

The use of computational methods to evaluate aesthetics in photography has gained interest in recent years due to the popularization of convolutional neural networks and the availability of new annotated datasets. Most studies in this area have focused on designing models that do not take into account individual preferences for the prediction of the aesthetic value of pictures. We propose a model based on residual learning that is capable of learning subjective, user specific preferences over aesthetics in photography, while surpassing the state-of-the-art methods and keeping a limited number of user-specific parameters in the model. Our model can also be used for picture enhancement, and it is suitable for content-based or hybrid recommender systems in which the amount of computational resources is limited.