# BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset

arXiv: https://arxiv.org/abs/2303.05325 · HTML: https://mlsanity.com/paper/2303.05325/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 14 of 14)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [A Survey on Optical Character Recognition System](https://mlsanity.com/paper/1710.05703/) (2017)
- [A Multiplexed Network for End-to-End, Multilingual OCR](https://mlsanity.com/paper/2103.15992/) (2021)
- [A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes](https://mlsanity.com/paper/2010.00170/) (2020)

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

- [TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking](https://mlsanity.com/paper/2502.11187/) (2025)
- [DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning](https://mlsanity.com/paper/2504.04085/) (2025)
- [IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing](https://mlsanity.com/paper/2512.20236/) (2025)
- [Performance Enhancement Leveraging Mask-RCNN on Bengali Document Layout Analysis](https://mlsanity.com/paper/2308.10511/) (2023)
- [bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents](https://mlsanity.com/paper/2308.10647/) (2023)
- [Bengali Document Layout Analysis with Detectron2](https://mlsanity.com/paper/2308.13769/) (2023)
- [Ensemble of Anchor-Free Models for Robust Bangla Document Layout Segmentation](https://mlsanity.com/paper/2308.14397/) (2023)
- [Document Layout Analysis on BaDLAD Dataset: A Comprehensive MViTv2 Based Approach](https://mlsanity.com/paper/2308.16571/) (2023)
- [Bengali Document Layout Analysis -- A YOLOV8 Based Ensembling Approach](https://mlsanity.com/paper/2309.00848/) (2023)
- [Framework and Model Analysis on Bengali Document Layout Analysis Dataset: BaDLAD](https://mlsanity.com/paper/2309.16700/) (2023)
- [HybriDLA: Hybrid Generation for Document Layout Analysis](https://mlsanity.com/paper/2511.19919/) (2025)
- [BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension](https://mlsanity.com/paper/2607.05614/) (2026)
- [Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms](https://mlsanity.com/paper/2607.21780/) (2026)

## Abstract (arXiv)

While strides have been made in deep learning based Bengali Optical Character Recognition (OCR) in the past decade, the absence of large Document Layout Analysis (DLA) datasets has hindered the application of OCR in document transcription, e.g., transcribing historical documents and newspapers. Moreover, rule-based DLA systems that are currently being employed in practice are not robust to domain variations and out-of-distribution layouts. To this end, we present the first multidomain large Bengali Document Layout Analysis Dataset: BaDLAD. This dataset contains 33,695 human annotated document samples from six domains - i) books and magazines, ii) public domain govt. documents, iii) liberation war documents, iv) newspapers, v) historical newspapers, and vi) property deeds, with 710K polygon annotations for four unit types: text-box, paragraph, image, and table. Through preliminary experiments benchmarking the performance of existing state-of-the-art deep learning architectures for English DLA, we demonstrate the efficacy of our dataset in training deep learning based Bengali document digitization models.