Papers › BEiT: BERT Pre-Training of Image Transformers

BEiT: BERT Pre-Training of Image Transformers

15 Jun 2021ICLR 2022 4arXiv:2106.08254archive 2025-07-28

Hangbo Bao, Li Dong, Songhao Piao, Furu Wei

We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first "tokenize" the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%). The code and pretrained models are available at https://aka.ms/beit.

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 11 code samples harvested from 3 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 9 samples from 2 repositories, 5 ran (3 with no instrument failure; 2 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.

No sample is linked to this paper from 6 of its repositories that Syntology harvested for other papers:

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

14 repositories listed; official and paper-mentioned ones first.

microsoft/unilm officialpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
E-DEEP/PapersReview mentioned on GitHubSyntology: not harvested report
facebookresearch/data2vec_vision mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
facebookresearch/vissl mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (2 instrument-failed) · 2 unverified report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
sunsmarterjie/itpn mentioned on GitHubpytorchSyntology: not harvested report
woctezuma/steam-BEiT mentioned on GitHubMITSyntology: not harvested report
yyk-wew/semanticmim mentioned on GitHubpytorchSyntology: not harvested report
2024-MindSpore-1/Code2 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code6 mindsporeSyntology: not harvested report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
pengzhiliang/MAE-pytorch pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/University mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 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. “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.

2ran; the contract check could not run
4ran
5unverified

Licence: 0 of the 11 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

microsoft/unilm official repository 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
beit/modeling_pretrain.py ran MIT (permissive) · 8d8f50f0e337e6ae · report fixture: returned Block · level recorded 2026-09-22
VisionTransformerForMaskedImageModeling beit/modeling_pretrain.py unverified MIT (permissive) · 40fe357c6531e542 · report
facebookresearch/data2vec_vision community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
beit/modeling_pretrain.py ran MIT (permissive) · b4267c3279f7dc9e · report fixture: returned PatchEmbed · level recorded 2026-09-22
VisionTransformerForMaskedImageModeling beit/modeling_pretrain.py unverified MIT (permissive) · c4156b300b1ba24f · report
facebookresearch/vissl community (archive-listed) 6 samples, 4 ran (2 instrument-failed) · 2 unverified
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
vissl/models/trunks/beit_transformer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · f4d723c4060a9c88 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
vissl/models/trunks/beit_transformer.py ran · metamorphic tier: invariant MIT (permissive) · d00d78c96a79991c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
vissl/models/trunks/beit_transformer.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 0233d6e8a07784ae · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vissl/models/trunks/beit_transformer.py ran; the contract check could not run (RAISES) MIT (permissive) · ab8464b48ee9d702 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22
BEiT vissl/models/trunks/beit_transformer.py unverified MIT (permissive) · 0b04b71ac3366634 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for BEIT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for BEIT (graph method: BEIT). 8 bricks; individually on a fixture: 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) · 3 unverified; every one of the 5 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. VisionTransformerForMaskedImageModeling entry · level 0 · unverified · c4156b300b1ba24f
  2. Block helper · level 0 · unverified · 514990276df7d1e1
  3. PatchEmbed helper · level 1 · ran · b4267c3279f7dc9e
  4. RelativePositionBias helper · level 1 · ran · d6e4999dab1a534a
  5. trunc_normal_ helper · level 0 · unverified · 08b4b321d2acf3db
  6. Attention helper · level 1 · ran · 2cddf6be601c390b
  7. DropPath helper · level 1 · ran · ea7880551588ee9f
  8. Mlp helper · level 1 · ran · e71525ebf968c4c3

harvested Assembly for BEIT (graph method: BEIT). 8 bricks; individually on a fixture: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. VisionTransformerForMaskedImageModeling entry · level 0 · unverified · 40fe357c6531e542
  2. Block helper · level 1 · ran · 8d8f50f0e337e6ae
  3. PatchEmbed helper · level 1 · ran · b4267c3279f7dc9e
  4. RelativePositionBias helper · level 1 · ran · d6e4999dab1a534a
  5. trunc_normal_ helper · level 0 · unverified · 08b4b321d2acf3db
  6. Attention helper · level 1 · ran · 2cddf6be601c390b
  7. DropPath helper · level 1 · ran · ea7880551588ee9f
  8. Mlp helper · level 1 · ran · e71525ebf968c4c3

harvested Assembly for BEIT (graph method: BEIT). 12 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. BEiT entry · level 0 · unverified · 0b04b71ac3366634
  2. AttrDict helper · level 1 · ran · 6663d33830e09bae
  3. Block model · level 0 · unverified · c8d115d51a70401e
  4. PatchEmbed model · level 1 · ran · d00d78c96a79991c
  5. RelativePositionBias model · level 1 · ran · d6e4999dab1a534a
  6. register_model_trunk helper · level 1 · ran · our draft was wrong · 4e819ea98b2a0bc8
  7. trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · ab8464b48ee9d702
  8. Attention model · level 1 · ran · 2cddf6be601c390b
  9. DropPath helper · level 1 · ran · f4d723c4060a9c88
  10. Mlp model · level 1 · ran · e71525ebf968c4c3
  11. drop_path helper · level 1 · ran; the contract check could not run (RAISES) · 0233d6e8a07784ae
  12. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · 813ed3a96c17cf42

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="2106.08254") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Document Image ClassificationDocument Layout AnalysisImage ClassificationSelf-Supervised Image ClassificationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Image Classification RVL-CDIP BEiT-B Accuracy 91.09% #27 of 31 Archive leaderboard report
Document Image Classification RVL-CDIP BEiT-B Parameters 87M #27 of 31 Archive leaderboard report
Document Layout Analysis PubLayNet val BEiT-B Figure 0.957 #11 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val BEiT-B List 0.924 #11 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val BEiT-B Overall 0.931 #11 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val BEiT-B Table 0.973 #11 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val BEiT-B Text 0.934 #11 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val BEiT-B Title 0.866 #11 of 15 Archive leaderboard report
Image Classification ImageNet BEiT-L (ViT; ImageNet-22K pretrain) Number of params 331M #37 of 1060 Archive leaderboard report
Image Classification ImageNet BEiT-L (ViT; ImageNet-22K pretrain) Top 1 Accuracy 88.60% #37 of 1060 Archive leaderboard report
Image Classification ImageNet BEiT-L (ViT; ImageNet 1k pretrain) Number of params 86M #158 of 1060 Archive leaderboard report
Image Classification ImageNet BEiT-L (ViT; ImageNet 1k pretrain) Top 1 Accuracy 86.3% #158 of 1060 Archive leaderboard report
Image Classification OmniBenchmark BeiT Average Top-1 Accuracy 30.1 #22 of 22 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) BEiT-L (ViT) Number of Params 307M #14 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) BEiT-L (ViT) Top 1 Accuracy 86.3% #14 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) BEiT-B (ViT) Number of Params 86M #29 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) BEiT-B (ViT) Top 1 Accuracy 84.6% #29 of 65 Archive leaderboard report
Semantic Segmentation ADE20K BEiT-L (ViT+UperNet) Validation mIoU 57.0 #35 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val BEiT-L (ViT+UperNet, ImageNet-22k pretrain) mIoU 57.0 #22 of 95 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

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPEDeiTDense ConnectionsDropoutFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerWeight DecayWordPiece

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