Photo Aesthetics Ranking Network with Attributes and Content Adaptation

TL;DR

This paper introduces a deep learning model for fine-grained photo aesthetics ranking that incorporates photographic attributes and content adaptation, trained on a new annotated database, achieving improved consistency with human judgments and state-of-the-art classification results.

Contribution

The work presents a novel deep neural network that jointly learns aesthetic attributes and content features, along with a new dataset and sampling strategy for robust aesthetic ranking.

Findings

Model outperforms previous methods in aesthetic ranking accuracy.

Achieves state-of-the-art classification on AVA dataset.

Sampling strategy effectively handles subjective aesthetic judgments.

Abstract

Real-world applications could benefit from the ability to automatically generate a fine-grained ranking of photo aesthetics. However, previous methods for image aesthetics analysis have primarily focused on the coarse, binary categorization of images into high- or low-aesthetic categories. In this work, we propose to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function. Our model incorporates joint learning of meaningful photographic attributes and image content information which can help regularize the complicated photo aesthetics rating problem. To train and analyze this model, we have assembled a new aesthetics and attributes database (AADB) which contains aesthetic scores and meaningful attributes assigned to each image by multiple human raters. Anonymized rater identities are recorded across images allowing us to exploit intra-rater consistency using a novel sampling strategy when computing the ranking loss of training image pairs. We show the proposed sampling strategy is very effective and robust in face of subjective judgement of image aesthetics by individuals with different aesthetic tastes. Experiments demonstrate that our unified model can generate aesthetic rankings that are more consistent with human ratings. To further validate our model, we show that by simply thresholding the estimated aesthetic scores, we are able to achieve state-or-the-art classification performance on the existing AVA dataset benchmark.