{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-graphical-approach-to-document-layout","title":"A Graphical Approach to Document Layout Analysis","arxiv_id":"2308.02051","date":"2023-08-03","proceeding":null,"authors":["Jilin Wang","Michael Krumdick","Baojia Tong","Hamima Halim","Maxim Sokolov","Vadym Barda","Delphine Vendryes","Chris Tanner"],"abstract":"Document layout analysis (DLA) is the task of detecting the distinct, semantic content within a document and correctly classifying these items into an appropriate category (e.g., text, title, figure). DLA pipelines enable users to convert documents into structured machine-readable formats that can then be used for many useful downstream tasks. Most existing state-of-the-art (SOTA) DLA models represent documents as images, discarding the rich metadata available in electronically generated PDFs. Directly leveraging this metadata, we represent each PDF page as a structured graph and frame the DLA problem as a graph segmentation and classification problem. We introduce the Graph-based Layout Analysis Model (GLAM), a lightweight graph neural network competitive with SOTA models on two challenging DLA datasets - while being an order of magnitude smaller than existing models. In particular, the 4-million parameter GLAM model outperforms the leading 140M+ parameter computer vision-based model on 5 of the 11 classes on the DocLayNet dataset. A simple ensemble of these two models achieves a new state-of-the-art on DocLayNet, increasing mAP from 76.8 to 80.8. Overall, GLAM is over 5 times more efficient than SOTA models, making GLAM a favorable engineering choice for DLA tasks.","url_abs":"https://arxiv.org/abs/2308.02051v1","url_pdf":"https://arxiv.org/pdf/2308.02051v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-graphical-approach-to-document-layout","repo_url":"https://github.com/ivanstepanovftw/glam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-layout-analysis","task_name":"Document Layout Analysis"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[{"method_slug":"dla","method_name":"DLA"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-layout-analysis-on-publaynet-val","task":"Document Layout Analysis","dataset":"PubLayNet val","model":"GLAM","rank_in_archive_order":14,"of":15,"metrics":{"Figure":"0.206","List":"0.862","Overall":"0.722","Table":"0.868","Text":"0.878","Title":"0.800"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.02051","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}