# Efficient Document Image Classification Using Region-Based Graph Neural Network

arXiv: https://arxiv.org/abs/2106.13802 · HTML: https://mlsanity.com/paper/2106.13802/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 25 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network](https://mlsanity.com/paper/1706.02337/) (2017)
- [Graph Convolution for Multimodal Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/1903.11279/) (2019)
- [DocBERT: BERT for Document Classification](https://mlsanity.com/paper/1904.08398/) (2019)
- [BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding](https://mlsanity.com/paper/1909.04948/) (2019)
- [Multimodal deep networks for text and image-based document classification](https://mlsanity.com/paper/1907.06370/) (2019)
- [Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification](https://mlsanity.com/paper/1704.03557/) (2017)
- [Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1801.09321/) (2018)
- [Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines](https://mlsanity.com/paper/1711.05862/) (2017)

## Built on by (most cited first, 3 of 3)

- [Domain Agnostic Few-Shot Learning For Document Intelligence](https://mlsanity.com/paper/2111.00007/) (2021)
- [End-to-End Document Classification and Key Information Extraction using Assignment Optimization](https://mlsanity.com/paper/2306.00750/) (2023)
- [DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documents](https://mlsanity.com/paper/2306.01359/) (2023)

## Abstract (arXiv)

Document image classification remains a popular research area because it can be commercialized in many enterprise applications across different industries. Recent advancements in large pre-trained computer vision and language models and graph neural networks has lent document image classification many tools. However using large pre-trained models usually requires substantial computing resources which could defeat the cost-saving advantages of automatic document image classification. In the paper we propose an efficient document image classification framework that uses graph convolution neural networks and incorporates textual, visual and layout information of the document. We have rigorously benchmarked our proposed algorithm against several state-of-art vision and language models on both publicly available dataset and a real-life insurance document classification dataset. Empirical results on both publicly available and real-world data show that our methods achieve near SOTA performance yet require much less computing resources and time for model training and inference. This results in solutions than offer better cost advantages, especially in scalable deployment for enterprise applications. The results showed that our algorithm can achieve classification performance quite close to SOTA. We also provide comprehensive comparisons of computing resources, model sizes, train and inference time between our proposed methods and baselines. In addition we delineate the cost per image using our method and other baselines.