EUFCC-340K: A Faceted Hierarchical Dataset for Metadata Annotation in GLAM Collections

TL;DR

This paper introduces EUFCC340K, a large hierarchical dataset for metadata annotation in GLAM collections, and develops baseline models to improve multi-label image tagging and cataloging in cultural heritage.

Contribution

The paper presents a new large-scale, hierarchically organized dataset and baseline models for multi-label metadata annotation in GLAM collections, addressing a key challenge in cultural heritage cataloging.

Findings

Baseline models show promising accuracy in multi-label classification.

The dataset improves robustness and generalization in metadata annotation tasks.

Models outperform existing methods on the new dataset.

Abstract

In this paper, we address the challenges of automatic metadata annotation in the domain of Galleries, Libraries, Archives, and Museums (GLAMs) by introducing a novel dataset, EUFCC340K, collected from the Europeana portal. Comprising over 340,000 images, the EUFCC340K dataset is organized across multiple facets: Materials, Object Types, Disciplines, and Subjects, following a hierarchical structure based on the Art & Architecture Thesaurus (AAT). We developed several baseline models, incorporating multiple heads on a ConvNeXT backbone for multi-label image tagging on these facets, and fine-tuning a CLIP model with our image text pairs. Our experiments to evaluate model robustness and generalization capabilities in two different test scenarios demonstrate the utility of the dataset in improving multi-label classification tools that have the potential to alleviate cataloging tasks in the cultural heritage sector.