Papers › Efficient Document Image Classification Using Region-Based Graph Neural Network

Efficient Document Image Classification Using Region-Based Graph Neural Network

25 Jun 2021arXiv:2106.13802archive 2025-07-28

Jaya Krishna Mandivarapu, Eric Bunch, Qian You, Glenn Fung

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.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification Document Classification Document Image Classification Graph Neural Network Image Classification document-image-classification image-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Document Image Classification	Tobacco-3482	DocBert [DOCBERT]	Accuracy	91.95	#2 of 10	Archive leaderboard	report
Document Image Classification	Tobacco-3482	Eff-GNN + Word2Vec [word2vec]	Accuracy	91	#3 of 10	Archive leaderboard	report
Document Image Classification	Tobacco-3482	DocBERT [DOCBERT]	Accuracy	82.3	#6 of 10	Archive leaderboard	report
Document Image Classification	Tobacco-3482	BERT [BERT]	Accuracy	79	#7 of 10	Archive leaderboard	report
Document Image Classification	Tobacco-3482	Eff-GNN + Word2Vec [word2vec] + Image Embedding	Accuracy	77.5	#8 of 10	Archive leaderboard	report
Document Image Classification	Tobacco-3482	Eff-GNN+ Word2Vec [word2vec]	Accuracy	73.5	#9 of 10	Archive leaderboard	report
Document Image Classification	Tobacco-3482	VGG	Memory	7.08	#10 of 10	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution Graph Convolutional Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections