Browse State-of-the-Art › Document Image Classification
Document Image Classification
25 papers with code · 8 benchmarks · 4 datasets archive 2025-07-28
Document image classification is the task of classifying documents based on images of their contents.
( Image credit: Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| RVL-CDIP (31 rows) | EAML | EAML: Ensemble Self-Attention-based Mutual Learning Network for... | — | — | Compare |
| Tobacco-3482 (10 rows) | DocXClassifier-L | DocXClassifier: High Performance Explainable Deep Network for... | code | — | Compare |
| Noisy Bangla Numeral (2 rows) | PCGAN-CHAR | PCGAN-CHAR: Progressively Trained Classifier Generative... | — | — | Compare |
| Noisy Bangla Characters (2 rows) | PCGAN-CHAR | PCGAN-CHAR: Progressively Trained Classifier Generative... | — | — | Compare |
| AIP (1 row) | ResNet-RS (ResNet-200 + RS training tricks) | Revisiting ResNets: Improved Training and Scaling Strategies | code | — | Compare |
| n-MNIST (1 row) | Pixel-level RC | Pixel-level Reconstruction and Classification for Noisy... | — | — | Compare |
| Noisy MNIST (1 row) | PCGAN-CHAR | PCGAN-CHAR: Progressively Trained Classifier Generative... | — | — | Compare |
| SUT (1 row) | CNN | SUT: a new multi-purpose synthetic dataset for Farsi document... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
4 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 50 · with a code link: 25 · where Syntology ran a sample: 10 (8 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (10 of 50 tagged: 8 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 50 of 50, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
26 Jul 2019 67 repositories listed Syntology community repositories only · 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified (of 48 harvested samples) · 24 pointer-only (licence)Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.
-
23 Dec 2020 40 repositories listed Syntology community repositories only · 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 19 harvested samples) · 3 pointer-only (licence)In this work, we produce a competitive convolution-free transformer by training on Imagenet only.
-
31 Dec 2019 19 repositories listed Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)In this paper, we propose the LayoutLM to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding…
-
15 Jun 2021 14 repositories listed Syntology official (archive's flag): 1 ran · 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 11 harvested samples)We first "tokenize" the original image into visual tokens.
-
29 Dec 2020 9 repositories listedPre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born…
-
18 Apr 2021 6 repositories listedIn this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding.
-
28 Feb 2022 5 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)LiLT can be pre-trained on the structured documents of a single language and then directly fine-tuned on other languages with the corresponding off-the-shelf monolingual/multilingual pre-trained textual models.
-
30 Nov 2021 5 repositories listed Syntology official (archive's flag): 1 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples)Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
-
11 Apr 2017 5 repositories listedWe present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half.
-
18 Apr 2022 4 repositories listedIn this paper, we propose LayoutLMv3 to pre-train multimodal Transformers for Document AI with unified text and image masking.
-
4 Mar 2022 4 repositories listed Syntology community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)We leverage DiT as the backbone network in a variety of vision-based Document AI tasks, including document image classification, document layout analysis, table detection as well as text detection for OCR.
-
29 Jan 2018 4 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)In this work, a region-based Deep Convolutional Neural Network framework is proposed for document structure learning.
-
13 Mar 2021 3 repositories listedUsing improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1.
-
28 Nov 2023 2 repositories listedDigital libraries often face the challenge of processing a large volume of diverse document types.
-
12 Oct 2022 2 repositories listed Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 1 pointer-only (licence)Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding.
-
21 May 2024 1 repository listedOur multimodal EE design preserves the model's predictive capabilities, enhancing both speed and latency.
-
27 Nov 2023 1 repository listedThis paper introduces a new large-scale dataset for Farsi document images, named SUT, which aims to tackle the challenges associated with obtaining diverse and substantial ground-truth data for supervised models in…
-
1 Mar 2023 1 repository listedCompared to the masked multi-modal modeling methods for document image understanding that rely on both the image and text modalities, StrucTexTv2 models image-only input and potentially deals with more application…
-
16 Jan 2023 1 repository listedIn this paper, we propose to exploit the side-tuning framework for multimodal document classification.
-
17 Mar 2022 1 repository listedOur approach achieves a new peak performance in image-based classification on two popular document datasets, namely RVL-CDIP and Tobacco3482, with a top-1 classification accuracy of 94.
-
22 Jun 2021 1 repository listed Syntology 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 5 samples that ran constructed an object rather than computing a result (of 10 harvested samples)DocFormer uses text, vision and spatial features and combines them using a novel multi-modal self-attention layer.
-
24 May 2021 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 5 unverified (of 5 harvested samples)Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks.
-
18 Feb 2021 1 repository listedWe address the challenging problem of Natural Language Comprehension beyond plain-text documents by introducing the TILT neural network architecture which simultaneously learns layout information, visual features, and…
-
16 Jun 2020 1 repository listedThis paper presents a study showing the benefits of the EfficientNet models compared with heavier Convolutional Neural Networks (CNNs) in the Document Classification task, essential problem in the digitalization process…
-
16 Apr 2020 1 repository listedAs a solution to this problem, we introduced a whole new architecture based on separable convolution.
-
Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models18 Dec 2024 0 repositories listedClassifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding.
-
17 Dec 2024 0 repositories listedThe advent of multimodal learning has brought a significant improvement in document AI.
-
DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification4 Jul 2024 0 repositories listedDeep learning (DL) has revolutionized the field of document image analysis, showcasing superhuman performance across a diverse set of tasks.
-
DistilDoc: Knowledge Distillation for Visually-Rich Document Applications12 Jun 2024 0 repositories listedThis work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC).
-
CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification6 May 2024 0 repositories listedZero-shot learning has been extensively investigated in the broader field of visual recognition, attracting significant interest recently.
-
LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding21 Mar 2024 0 repositories listed
-
A Multi-Modal Multilingual Benchmark for Document Image Classification25 Oct 2023 0 repositories listed
-
11 Sep 2023 0 repositories listed
-
30 May 2023 0 repositories listed
-
11 May 2023 0 repositories listed
-
Evaluating Adversarial Robustness on Document Image Classification24 Apr 2023 0 repositories listed
-
Context-Aware Classification of Legal Document Pages5 Apr 2023 0 repositories listed
-
24 May 2022 0 repositories listed
-
Document AI: Benchmarks, Models and Applications16 Nov 2021 0 repositories listed
-
Domain Agnostic Few-Shot Learning For Document Intelligence29 Oct 2021 0 repositories listed
-
25 Jun 2021 0 repositories listed
-
14 Jun 2021 0 repositories listed
-
16 Jun 2020 0 repositories listed
-
Self-Supervised Representation Learning on Document Images18 Apr 2020 0 repositories listed
-
11 Aug 2019 0 repositories listed
-
21 Jun 2018 0 repositories listed
-
Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines3 Nov 2017 0 repositories listed
-
10 Aug 2017 0 repositories listed
-
Document image classification, with a specific view on applications of patent images13 Jan 2016 0 repositories listed
-
25 Feb 2015 0 repositories listed
Syntology lines on 11 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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