A Computational Approach to Relative Aesthetics

TL;DR

This paper introduces a novel deep learning approach for ranking images based on aesthetic quality, moving beyond binary classification to relative ranking, and demonstrates improved accuracy on a new dataset of image pairs.

Contribution

It formulates the problem of aesthetic ranking using relative labels and proposes a deep neural network trained with relative learning principles, outperforming existing binary classification methods.

Findings

The proposed method achieves higher ranking accuracy than state-of-the-art binary classifiers.

A new dataset of image pairs with relative aesthetic labels is constructed from AVA.

Relative training improves the model's ability to rank images by aesthetic quality.

Abstract

Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such applications, it may be possible that all images belong to the same category. Hence determining the aesthetic ranking of the images is more appropriate. To this end, we formulate a novel problem of ranking images with respect to their aesthetic quality. We construct a new dataset of image pairs with relative labels by carefully selecting images from the popular AVA dataset. Unlike in aesthetics classification, there is no single threshold which would determine the ranking order of the images across our entire dataset. We propose a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows our network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels.