SciOL and MuLMS-Img: Introducing a Large-Scale Multimodal Scientific Dataset and Models for Image-Text Tasks in the Scientific Domain

Tim Tarsi, Heike Adel, Jan Hendrik Metzen, Dan Zhang, Matteo Finco, Annemarie Friedrich; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 4560-4571

In scientific publications, a substantial part of the information is expressed via figures containing images and diagrams. Hence, the retrieval of relevant figures given a natural language query is an important real-world task. However, due to the lack of training and evaluation data, most existing approaches are either limited to one modality or focus on non-scientific domains, making their application to scientific publications challenging. In this paper, we address this gap by introducing two novel datasets: (1) SciOL, the largest openly-licensed pre-training corpus for multimodal models in the scientific domain, covering multiple sciences including materials science, physics, and computer science, and (2) MuLMS-Img, a high-quality dataset in the materials science domain, manually annotated for various image-text tasks. Our experiments show that pre-training large-scale vision-language models on SciOL increases performance considerably across a broad variety of image-text tasks including figure type classification, optical character recognition, captioning, and figure retrieval. Using MuLMS-Img, we show that integrating text-based features extracted via a fine-tuned model for a specific domain can boost cross-modal scientific figure retrieval performance by up to 50%.