Papers › DocFormer: End-to-End Transformer for Document Understanding

DocFormer: End-to-End Transformer for Document Understanding

22 Jun 2021ICCV 2021 10arXiv:2106.11539archive 2025-07-28

Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, R. Manmatha

We present DocFormer -- a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU). VDU is a challenging problem which aims to understand documents in their varied formats (forms, receipts etc.) and layouts. In addition, DocFormer is pre-trained in an unsupervised fashion using carefully designed tasks which encourage multi-modal interaction. DocFormer uses text, vision and spatial features and combines them using a novel multi-modal self-attention layer. DocFormer also shares learned spatial embeddings across modalities which makes it easy for the model to correlate text to visual tokens and vice versa. DocFormer is evaluated on 4 different datasets each with strong baselines. DocFormer achieves state-of-the-art results on all of them, sometimes beating models 4x its size (in no. of parameters).

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 10 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

shabie/docformer mentioned on GitHubpytorchSyntology: 10 samples, 5 ran (0 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran
5unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from shabie/docformer. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

shabie/docformer community (archive-listed) 10 samples, 5 ran (0 instrument-failed) · 5 unverified
MultiModalAttentionLayer src/docformer/modeling.py ran MIT (permissive) · 08d9b843959a11da · report fixture: returned MultiModalAttentionLayer · level recorded 2026-09-22
PositionalEncoding in 126 papers
census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket
src/docformer/modeling.py ran MIT (permissive) · 95c11b9646ef2995 · report fixture: returned PositionalEncoding · level recorded 2026-09-22
PreNormAttn src/docformer/modeling.py ran MIT (permissive) · 9d44110b605b91c8 · report fixture: returned PreNormAttn · level recorded 2026-09-22
RelativePosition src/docformer/modeling.py ran MIT (permissive) · 2485d54f61db9f8d · report fixture: returned RelativePosition · level recorded 2026-09-22
ResNetFeatureExtractor src/docformer/modeling.py ran MIT (permissive) · 3c51327ee452d265 · report fixture: returned ResNetFeatureExtractor · level recorded 2026-09-22
DocFormer src/docformer/modeling.py unverified MIT (permissive) · b7af5dd1c0383ff1 · report
DocFormerEmbeddings src/docformer/modeling.py unverified MIT (permissive) · 4006b85007037117 · report
DocFormerEncoder src/docformer/modeling.py unverified MIT (permissive) · 682dbc1c67b2b9df · report
ExtractFeatures src/docformer/modeling.py unverified MIT (permissive) · 714cd85a4f672596 · report
LanguageFeatureExtractor src/docformer/modeling.py unverified MIT (permissive) · 330baaddd559fac9 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for DocFormer (graph method: DocFormer). 12 bricks; individually on a fixture: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 7 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. DocFormer entry · level 0 · unverified · b7af5dd1c0383ff1
  2. DocFormerEncoder model · level 0 · unverified · 682dbc1c67b2b9df
  3. ExtractFeatures helper · level 0 · unverified · 714cd85a4f672596
  4. FeedForward model · level 1 · ran · 450f5b303bbc3417
  5. MultiModalAttentionLayer model · level 1 · ran · 08d9b843959a11da
  6. PreNorm model · level 1 · ran · 9b66b60a7704b891
  7. PreNormAttn model · level 1 · ran · 9d44110b605b91c8
  8. DocFormerEmbeddings model · level 0 · unverified · 4006b85007037117
  9. LanguageFeatureExtractor model · level 0 · unverified · 330baaddd559fac9
  10. ResNetFeatureExtractor model · level 1 · ran · 3c51327ee452d265
  11. RelativePosition model · level 1 · ran · 2485d54f61db9f8d
  12. PositionalEncoding model · level 1 · ran · 95c11b9646ef2995

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.11539") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Document Image Classificationdocument understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Image Classification RVL-CDIP DocFormerBASE Accuracy 96.17% #3 of 31 Archive leaderboard report
Document Image Classification RVL-CDIP DocFormerBASE Parameters 183M #3 of 31 Archive leaderboard report
Document Image Classification RVL-CDIP DocFormer large Accuracy 95.50% #8 of 31 Archive leaderboard report
Document Image Classification RVL-CDIP DocFormer large Parameters 536M #8 of 31 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.

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