Papers › Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation

Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation

12 May 2021arXiv:2105.05537archive 2025-07-28

Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, Manning Wang

In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis. Especially, the deep neural networks based on U-shaped architecture and skip-connections have been widely applied in a variety of medical image tasks. However, although CNN has achieved excellent performance, it cannot learn global and long-range semantic information interaction well due to the locality of the convolution operation. In this paper, we propose Swin-Unet, which is an Unet-like pure Transformer for medical image segmentation. The tokenized image patches are fed into the Transformer-based U-shaped Encoder-Decoder architecture with skip-connections for local-global semantic feature learning. Specifically, we use hierarchical Swin Transformer with shifted windows as the encoder to extract context features. And a symmetric Swin Transformer-based decoder with patch expanding layer is designed to perform the up-sampling operation to restore the spatial resolution of the feature maps. Under the direct down-sampling and up-sampling of the inputs and outputs by 4x, experiments on multi-organ and cardiac segmentation tasks demonstrate that the pure Transformer-based U-shaped Encoder-Decoder network outperforms those methods with full-convolution or the combination of transformer and convolution. The codes and trained models will be publicly available at https://github.com/HuCaoFighting/Swin-Unet.

PaperPDFCodeCode Syntology ran

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

The archive's official repository (HuCaoFighting/Swin-Unet) was not harvested; the 18 samples below come from 2 community repositories.

Syntology 18 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 2 repositories, 17 ran (14 with no instrument failure; 3 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

HuCaoFighting/Swin-Unet officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
Arnukk/CASPIAN mentioned on GitHubtfMITSyntology: 9 samples, 8 ran (3 instrument-failed) · 1 unverified report
WonJunPark/swinUNet_custom_training mentioned on GitHubpytorchSyntology: not harvested report
simonustc/mcpa-for-2d-medical-image-segmentation mentioned on GitHubpytorchSyntology: not harvested report
yingkaisha/keras-unet-collection mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical... (arXiv:1802.06955; that paper's own run record: 5 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; 5 where Syntology's instrument failed) · 3 unverified), Attention U-Net: Learning Where to Look for the Pancreas (arXiv:1804.03999; that paper's own run record: 23 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified), ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data (arXiv:1904.00592; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
L-A-Sandhu/Swin-Unet- tfMITSyntology: 9 samples, 9 ran (0 instrument-failed) · 0 unverified report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested 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

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 1 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.

1ran · our draft was wrong
2ran; the contract check could not run
14ran
1unverified

Licence: 0 of the 18 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 2 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”. “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.

Arnukk/CASPIAN community (archive-listed) 9 samples, 8 ran (3 instrument-failed) · 1 unverified
clear_ds utils.py ran MIT (permissive) · f4820de6705b381d · report fixture: signature f:NoneType/0/?, x:EagerTensor/2/float, y:EagerTensor/2/float, yf:EagerTensor/2/float, one_d:bool/0/bool · returned tuple · level recorded 2026-09-24
drop_path_ in 5 papers models/keras_vision_transformer/util_layers.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 4bbaba82e75c9aff · report fixture: signature inputs:EagerTensor/4/float, drop_prob:float/0/float, is_training:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
find_scenario utils.py ran MIT (permissive) · 4a0971f8b14ed3d9 · report fixture: signature scenario:EagerTensor/0/int · returned function · level recorded 2026-09-24
image_to_array models/keras_vision_transformer/utils.py ran MIT (permissive) · 49481c5cc405f648 · report fixture: signature filenames:list/1/str, size:int/0/int, channel:int/0/int · returned ndarray · level recorded 2026-09-24
rmv_aug utils.py ran MIT (permissive) · 17e354bf251f8085 · report fixture: signature f:str/0/str, x:NoneType/0/?, y:NoneType/0/?, yf:NoneType/0/? · returned bool · level recorded 2026-09-24
shuffle_ind models/keras_vision_transformer/utils.py ran fingerprinted MIT (permissive) · 8802de1b1b8688a8 · report fixture: signature L:int/0/int · returned ndarray · level recorded 2026-09-24
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/keras_vision_transformer/swin_layers.py ran · our draft was wrong fingerprinted MIT (permissive) · dd1296fb557f6f49 · report fixture: signature x:EagerTensor/4/float, window_size:int/0/int · returned EagerTensor · level recorded 2026-09-22
window_reverse in 296 papers models/keras_vision_transformer/swin_layers.py ran; the contract check could not run (RAISES) MIT (permissive) · 24a9365e0448ac64 · report fixture: signature windows:EagerTensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int, C:int/0/int · returned EagerTensor · level recorded 2026-09-22
dummy_loader models/keras_vision_transformer/utils.py unverified MIT (permissive) · f4c0270069e690f7 · report
L-A-Sandhu/Swin-Unet- community (archive-listed) 9 samples, 9 ran (0 instrument-failed) · 0 unverified
bce_loss_fn src/swin_transformer/AUC_LOSS.py ran MIT (permissive) · dda41d1bd5f7d32e · report fixture: signature label_smoothing:float/0/float · returned BCELoss · level recorded 2026-09-24
compute_binary_metrics src/swin_transformer/metrics.py ran MIT (permissive) · d5165a7134b3051a · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int, y_prob:ndarray/1/float · returned dict · level recorded 2026-09-24
compute_multiclass_metrics src/swin_transformer/metrics.py ran MIT (permissive) · 14ef6380261ac759 · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int, num_classes:int/0/int · returned dict · level recorded 2026-09-24
dice_loss_fn src/swin_transformer/AUC_LOSS.py ran MIT (permissive) · 9c8302514c4e7b35 · report fixture: signature smooth:float/0/float · returned DiceLoss · level recorded 2026-09-24
dummy_loader src/keras_swin_unet/utils.py ran MIT (permissive) · db4d0a3eecb8e0db · report fixture: signature model_path:str/0/str · returned list · level recorded 2026-09-24
focal_loss in 65 papers
census: 6 implementations from 13 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
src/swin_transformer/AUC_LOSS.py ran MIT (permissive) · dc39ed696312e230 · report fixture: signature alpha:float/0/float, gamma:float/0/float, label_smoothing:float/0/float · returned FocalLoss · level recorded 2026-09-24
image_to_array src/keras_swin_unet/utils.py ran MIT (permissive) · 8e18cbe83a5ae888 · report fixture: signature filenames:list/1/str, size:int/0/int, channel:int/0/int · returned ndarray · level recorded 2026-09-24
shuffle_ind src/keras_swin_unet/utils.py ran fingerprinted MIT (permissive) · 000032b4e43a1534 · report fixture: signature L:int/0/int · returned ndarray · level recorded 2026-09-24
split_dataset in 65 papers src/swin_transformer/split_data.py ran MIT (permissive) · 17f6210c3a9f9f5b · report fixture: signature ids:list/1/int, train_frac:float/0/float, val_frac:float/0/float, test_frac:float/0/float · returned tuple · level recorded 2026-09-24

Tasks

Cardiac SegmentationDecoderImage SegmentationMedical Image AnalysisMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation ACDC Swin UNet Dice Score 0.9 #5 of 6 Archive leaderboard report
Medical Image Segmentation Automatic Cardiac Diagnosis Challenge (ACDC) SwinUnet Avg DSC 90.00 #16 of 20 Archive leaderboard report
Medical Image Segmentation Synapse multi-organ CT SwinUnet Avg DSC 79.13 #21 of 23 Archive leaderboard report
Medical Image Segmentation Synapse multi-organ CT SwinUnet Avg HD 21.55 #21 of 23 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 EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformer

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