# SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction

arXiv: https://arxiv.org/abs/2410.01609 · HTML: https://mlsanity.com/paper/2410.01609/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [SelfDoc: Self-Supervised Document Representation Learning](https://mlsanity.com/paper/2106.03331/) (2021)
- [xGen-MM (BLIP-3): A Family of Open Large Multimodal Models](https://mlsanity.com/paper/2408.08872/) (2024)
- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://mlsanity.com/paper/2202.13669/) (2022)
- [LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding](https://mlsanity.com/paper/2404.05225/) (2024)
- [Compressing Visual-linguistic Model via Knowledge Distillation](https://mlsanity.com/paper/2104.02096/) (2021)
- [Unified Pretraining Framework for Document Understanding](https://mlsanity.com/paper/2204.10939/) (2022)
- [Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution](https://mlsanity.com/paper/2102.06732/) (2021)
- [Transfer Learning with Dynamic Distribution Adaptation](https://mlsanity.com/paper/1909.08531/) (2019)
- [Deep Learning based Visually Rich Document Content Understanding: A Survey](https://mlsanity.com/paper/2408.01287/) (2024)
- [Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis](https://mlsanity.com/paper/2208.10970/) (2022)
- [Form-NLU: Dataset for the Form Natural Language Understanding](https://mlsanity.com/paper/2304.01577/) (2023)
- [StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond](https://mlsanity.com/paper/2405.21013/) (2024)
- [3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding](https://mlsanity.com/paper/2402.17983/) (2024)
- [Multimodal Document Analytics for Banking Process Automation](https://mlsanity.com/paper/2307.11845/) (2023)
- [On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval](https://mlsanity.com/paper/2311.00693/) (2023)

## Built on by (most cited first, 4 of 4)

- [VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding](https://mlsanity.com/paper/2506.01388/) (2025)
- [Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding](https://mlsanity.com/paper/2601.12260/) (2026)
- [DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth](https://mlsanity.com/paper/2607.16203/) (2026)
- [MineTRACE: An Evidence-Grounded Interactive Reasoning System for Mineral Prospectivity](https://mlsanity.com/paper/2609.02060/) (2026)

## Abstract (arXiv)

Visually Rich Documents (VRDs), comprising elements such as charts, tables, and paragraphs, convey complex information across diverse domains. However, extracting key information from these documents remains labour-intensive, particularly for scanned formats with inconsistent layouts and domain-specific requirements. Despite advances in pretrained models for VRD understanding, their dependence on large annotated datasets for fine-tuning hinders scalability. This paper proposes SynJAC (Synthetic-data-driven Joint-granular Adaptation and Calibration), a method for key information extraction in scanned documents. SynJAC leverages synthetic, machine-generated data for domain adaptation and employs calibration on a small, manually annotated dataset to mitigate noise. By integrating fine-grained and coarse-grained document representation learning, SynJAC significantly reduces the need for extensive manual labelling while achieving competitive performance. Extensive experiments demonstrate its effectiveness in domain-specific and scanned VRD scenarios.