# DLAFormer: An End-to-End Transformer For Document Layout Analysis arXiv: https://arxiv.org/abs/2405.11757 ยท HTML: https://mlsanity.com/paper/2405.11757/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 37 of its 57 references that are in the map. - First posted on arXiv 20 May 2024. ## Builds on (most cited first, 30 of 37) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021) - [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015) - [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020) - [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017) - [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020) - [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021) - [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013) - [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022) - [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020) - [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022) - [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022) - [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022) - [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019) - [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021) - [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019) - [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016) - [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020) - [Fast Convergence of DETR with Spatially Modulated Co-Attention](https://mlsanity.com/paper/2101.07448/) (2021) - [DiT: Self-supervised Pre-training for Document Image Transformer](https://mlsanity.com/paper/2203.02378/) (2022) - [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022) - [Towards End-to-End Unified Scene Text Detection and Layout Analysis](https://mlsanity.com/paper/2203.15143/) (2022) - [Unified Pretraining Framework for Document Understanding](https://mlsanity.com/paper/2204.10939/) (2022) - [LayoutReader: Pre-training of Text and Layout for Reading Order Detection](https://mlsanity.com/paper/2108.11591/) (2021) - [VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations](https://mlsanity.com/paper/2105.06220/) (2021) - [HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures](https://mlsanity.com/paper/2303.13839/) (2023) - [Graphical Object Detection in Document Images](https://mlsanity.com/paper/2008.10843/) (2020) - [DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer](https://mlsanity.com/paper/2201.11438/) (2022) - [Post-OCR Paragraph Recognition by Graph Convolutional Networks](https://mlsanity.com/paper/2101.12741/) (2021) ## Built on by (most cited first, 11 of 11) - [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025) - [Document Intelligence in the Era of Large Language Models: A Survey](https://mlsanity.com/paper/2510.13366/) (2025) - [UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis](https://mlsanity.com/paper/2503.15893/) (2025) - [BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction](https://mlsanity.com/paper/2503.19658/) (2025) - [PARL: Position-Aware Relation Learning Network for Document Layout Analysis](https://mlsanity.com/paper/2601.07620/) (2026) - [From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding](https://mlsanity.com/paper/2602.07645/) (2026) - [TextBite: A Historical Czech Document Dataset for Logical Page Segmentation](https://mlsanity.com/paper/2503.16664/) (2025) - [LIGHT: Multi-Modal Text Linking on Historical Maps](https://mlsanity.com/paper/2506.22589/) (2025) - [HybriDLA: Hybrid Generation for Document Layout Analysis](https://mlsanity.com/paper/2511.19919/) (2025) - [Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing](https://mlsanity.com/paper/2604.02692/) (2026) - [Bounding Box Label Propagation for Re-Annotation of Document Layout Analysis Datasets](https://mlsanity.com/paper/2606.17644/) (2026) ## Abstract (arXiv) Document layout analysis (DLA) is crucial for understanding the physical layout and logical structure of documents, serving information retrieval, document summarization, knowledge extraction, etc. However, previous studies have typically used separate models to address individual sub-tasks within DLA, including table/figure detection, text region detection, logical role classification, and reading order prediction. In this work, we propose an end-to-end transformer-based approach for document layout analysis, called DLAFormer, which integrates all these sub-tasks into a single model. To achieve this, we treat various DLA sub-tasks (such as text region detection, logical role classification, and reading order prediction) as relation prediction problems and consolidate these relation prediction labels into a unified label space, allowing a unified relation prediction module to handle multiple tasks concurrently. Additionally, we introduce a novel set of type-wise queries to enhance the physical meaning of content queries in DETR. Moreover, we adopt a coarse-to-fine strategy to accurately identify graphical page objects. Experimental results demonstrate that our proposed DLAFormer outperforms previous approaches that employ multi-branch or multi-stage architectures for multiple tasks on two document layout analysis benchmarks, DocLayNet and Comp-HRDoc.