Stylistic Multi-Task Analysis of Ukiyo-e Woodblock Prints

TL;DR

This paper explores the pre-modern Japanese art form Ukiyo-e with the aim of broadening the scope for stylistic analysis and to provide a benchmark to evaluate a variety of art focused Computer Vision approaches.

Abstract

In this work we present a large-scale dataset of \textit{Ukiyo-e} woodblock prints. Unlike previous works and datasets in the artistic domain that primarily focus on western art, this paper explores this pre-modern Japanese art form with the aim of broadening the scope for stylistic analysis and to provide a benchmark to evaluate a variety of art focused Computer Vision approaches. Our dataset consists of over $175.000$ prints with corresponding metadata (\eg artist, era, and creation date) from the 17th century to present day. By approaching stylistic analysis as a Multi-Task problem we aim to more efficiently utilize the available metadata, and learn more general representations of style. We show results for well-known baselines and state-of-the-art multi-task learning frameworks to enable future comparison, and to encourage stylistic analysis on this artistic domain.

Figures (4)

• Figure 1: Ukiyo-e print with attributes from the proposed dataset.
• Figure 2: Examples of pairs of Ukiyo-e prints made from the same woodblock but with a different appearance.
• Figure 3: Stylistic Multi-task analysis model architecture.
• Figure 4: Attention maps for partially frozen ViT model trained with single task artist prediction (b), single task era prediction (c), and multi-task artist & era prediction (d).