preprint · arXiv (Cornell University) · 2025

SFDLA: Source-Free Document Layout Analysis

Tewes, Sebastian, Chen, Yufan, Moured, Omar, Zhang, Jiaming, Stiefelhagen, Rainer

Cited by 0Open access

Abstract

Document Layout Analysis (DLA) is a fundamental task in document understanding. However, existing DLA and adaptation methods often require access to large-scale source data and target labels. This requirements severely limiting their real-world applicability, particularly in privacy-sensitive and resource-constrained domains, such as financial statements, medical records, and proprietary business documents. According to our observation, directly transferring source-domain fine-tuned models on target domains often results in a significant performance drop (Avg. -32.64%). In this work, we introduce Source-Free Document Layout Analysis (SFDLA), aiming for adapting a pre-trained source DLA models to an unlabeled target domain, without access to any source data. To address this challenge, we establish the first SFDLA benchmark, covering three major DLA datasets for geometric- and content-aware adaptation. Furthermore, we propose Document Layout Analysis Adapter (DLAdapter), a novel framework that is designed to improve source-free adaptation across document domains. Our method achieves a +4.21% improvement over the source-only baseline and a +2.26% gain over existing source-free methods from PubLayNet to DocLayNet. We believe this work will inspire the DLA community to further investigate source-free document understanding. To support future research of the community, the benchmark, models, and code will be publicly available at https://github.com/s3setewe/sfdla-DLAdapter.

Cite this paper

APA 7

Tewes, S., Chen, Y., Moured, O., Zhang, J., & Stiefelhagen, R. (2025). SFDLA: Source-Free Document Layout Analysis. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2503.18742

MLA 9

Tewes, Sebastian, et al. “SFDLA: Source-Free Document Layout Analysis.” arXiv (Cornell University), 2025, https://doi.org/10.48550/arxiv.2503.18742.

Chicago

Tewes, Sebastian, Yufan Chen, Omar Moured, Jiaming Zhang, and Rainer Stiefelhagen. 2025. “SFDLA: Source-Free Document Layout Analysis.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2503.18742.

Harvard

Tewes, S. et al. (2025) ‘SFDLA: Source-Free Document Layout Analysis’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.2503.18742.

BibTeX

@misc{tewes2025sfdla,
  title = {{SFDLA: Source-Free Document Layout Analysis}},
  author = {Tewes, Sebastian and Chen, Yufan and Moured, Omar and Zhang, Jiaming and Stiefelhagen, Rainer},
  journal = {arXiv (Cornell University)},
  year = {2025},
  doi = {10.48550/arxiv.2503.18742}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.