Aesthetic Attributes Assessment of Images

TL;DR

This paper introduces a novel approach for assessing image aesthetic attributes by predicting descriptive captions and scores for multiple attributes, utilizing a new dataset and a transfer learning-based multi-attribute network.

Contribution

It proposes a new aesthetic attributes captioning framework, a novel dataset, and a multi-attribute network that jointly predicts captions and scores, advancing image aesthetic assessment methods.

Findings

Our method accurately predicts aesthetic attribute captions and scores.

The proposed AMAN outperforms traditional CNN-LSTM and SCA-CNN models.

Experimental results validate the effectiveness of transfer learning in this task.

Abstract

Image aesthetic quality assessment has been a relatively hot topic during the last decade. Most recently, comments type assessment (aesthetic captions) has been proposed to describe the general aesthetic impression of an image using text. In this paper, we propose Aesthetic Attributes Assessment of Images, which means the aesthetic attributes captioning. This is a new formula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute. We introduce a new dataset named \emph{DPC-Captions} which contains comments of up to 5 aesthetic attributes of one image through knowledge transfer from a full-annotated small-scale dataset. Then, we propose Aesthetic Multi-Attribute Network (AMAN), which is trained on a mixture of fully-annotated small-scale PCCD dataset and weakly-annotated large-scale DPC-Captions dataset. Our AMAN makes full use of transfer learning and attention model in a single framework. The experimental results on our DPC-Captions and PCCD dataset reveal that our method can predict captions of 5 aesthetic attributes together with numerical score assessment of each attribute. We use the evaluation criteria used in image captions to prove that our specially designed AMAN model outperforms traditional CNN-LSTM model and modern SCA-CNN model of image captions.