# RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

arXiv: https://arxiv.org/abs/2403.14442 · HTML: https://mlsanity.com/paper/2403.14442/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 78 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 30 of 56)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [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)
- [Understanding The Robustness in Vision Transformers](https://mlsanity.com/paper/2204.12451/) (2022)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [Benchmarking the Robustness of Semantic Segmentation Models](https://mlsanity.com/paper/1908.05005/) (2019)
- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://mlsanity.com/paper/2202.13669/) (2022)
- [Towards End-to-End Unified Scene Text Detection and Layout Analysis](https://mlsanity.com/paper/2203.15143/) (2022)
- [Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network](https://mlsanity.com/paper/1706.02337/) (2017)
- [StrucTexT: Structured Text Understanding with Multi-Modal Transformers](https://mlsanity.com/paper/2108.02923/) (2021)
- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)

## Built on by (most cited first, 13 of 13)

- [RoHOI: Robustness Benchmark for Human-Object Interaction Detection](https://mlsanity.com/paper/2507.09111/) (2025)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents](https://mlsanity.com/paper/2607.11192/) (2026)
- [CHAOS: Chart Analysis with Outlier Samples](https://mlsanity.com/paper/2505.17235/) (2025)
- [Robustness Evaluation of OCR-based Visual Document Understanding under Multi-Modal Adversarial Attacks](https://mlsanity.com/paper/2506.16407/) (2025)
- [IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing](https://mlsanity.com/paper/2512.20236/) (2025)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [Text-guided Feature Disentanglement for Cross-modal Gait Recognition](https://mlsanity.com/paper/2605.30784/) (2026)
- [EDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation](https://mlsanity.com/paper/2502.16541/) (2025)
- [DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification](https://mlsanity.com/paper/2508.04233/) (2025)
- [How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence](https://mlsanity.com/paper/2605.19309/) (2026)
- [LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing](https://mlsanity.com/paper/2608.16763/) (2026)
- [Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation](https://mlsanity.com/paper/2610.20335/) (2026)

## Abstract (arXiv)

Before developing a Document Layout Analysis (DLA) model in real-world applications, conducting comprehensive robustness testing is essential. However, the robustness of DLA models remains underexplored in the literature. To address this, we are the first to introduce a robustness benchmark for DLA models, which includes 450K document images of three datasets. To cover realistic corruptions, we propose a perturbation taxonomy with 36 common document perturbations inspired by real-world document processing. Additionally, to better understand document perturbation impacts, we propose two metrics, Mean Perturbation Effect (mPE) for perturbation assessment and Mean Robustness Degradation (mRD) for robustness evaluation. Furthermore, we introduce a self-titled model, i.e., Robust Document Layout Analyzer (RoDLA), which improves attention mechanisms to boost extraction of robust features. Experiments on the proposed benchmarks (PubLayNet-P, DocLayNet-P, and M6Doc-P) demonstrate that RoDLA obtains state-of-the-art mRD scores of 115.7, 135.4, and 150.4, respectively. Compared to previous methods, RoDLA achieves notable improvements in mAP of +3.8%, +7.1% and +12.1%, respectively.