OmniArt: Multi-task Deep Learning for Artistic Data Analysis
This work addresses the expensive process of categorical analysis in the artistic domain, though it appears incremental as it applies existing multi-task learning techniques to this specific area.
The authors tackled the problem of analyzing vast amounts of scattered artistic data by proposing an efficient multi-task deep learning method, which outperformed handcrafted features and convolutional neural networks on a new dataset of almost half a million samples.
Vast amounts of artistic data is scattered on-line from both museums and art applications. Collecting, processing and studying it with respect to all accompanying attributes is an expensive process. With a motivation to speed up and improve the quality of categorical analysis in the artistic domain, in this paper we propose an efficient and accurate method for multi-task learning with a shared representation applied in the artistic domain. We continue to show how different multi-task configurations of our method behave on artistic data and outperform handcrafted feature approaches as well as convolutional neural networks. In addition to the method and analysis, we propose a challenge like nature to the new aggregated data set with almost half a million samples and structured meta-data to encourage further research and societal engagement.