AVA: A large-scale database for aesthetic visual analysis

TLDR

The growing volume of visual content makes organizing it by aesthetic preference increasingly important, and early research into computational models of aesthetic preference shows great potential. The study aims to provide a realistic, diverse, and challenging database to advance aesthetic visual analysis research. AVA is a large‑scale database of over 250,000 images, each annotated with numerous aesthetic scores, more than 60 semantic categories, and photographic style labels. AVA outperforms existing databases in scale, diversity, and annotation heterogeneity, yields key insights into aesthetic preference, and improves performance on preference tasks in three applications.

Abstract

With the ever-expanding volume of visual content available, the ability to organize and navigate such content by aesthetic preference is becoming increasingly important. While still in its nascent stage, research into computational models of aesthetic preference already shows great potential. However, to advance research, realistic, diverse and challenging databases are needed. To this end, we introduce a new large-scale database for conducting Aesthetic Visual Analysis: AVA. It contains over 250,000 images along with a rich variety of meta-data including a large number of aesthetic scores for each image, semantic labels for over 60 categories as well as labels related to photographic style. We show the advantages of AVA with respect to existing databases in terms of scale, diversity, and heterogeneity of annotations. We then describe several key insights into aesthetic preference afforded by AVA. Finally, we demonstrate, through three applications, how the large scale of AVA can be leveraged to improve performance on existing preference tasks.