Papers › CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows

1 Jul 2021CVPR 2022 1arXiv:2107.00652archive 2025-07-28

Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, Baining Guo

We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute whereas local self-attention often limits the field of interactions of each token. To address this issue, we develop the Cross-Shaped Window self-attention mechanism for computing self-attention in the horizontal and vertical stripes in parallel that form a cross-shaped window, with each stripe obtained by splitting the input feature into stripes of equal width. We provide a mathematical analysis of the effect of the stripe width and vary the stripe width for different layers of the Transformer network which achieves strong modeling capability while limiting the computation cost. We also introduce Locally-enhanced Positional Encoding (LePE), which handles the local positional information better than existing encoding schemes. LePE naturally supports arbitrary input resolutions, and is thus especially effective and friendly for downstream tasks. Incorporated with these designs and a hierarchical structure, CSWin Transformer demonstrates competitive performance on common vision tasks. Specifically, it achieves 85.4% Top-1 accuracy on ImageNet-1K without any extra training data or label, 53.9 box AP and 46.4 mask AP on the COCO detection task, and 52.2 mIOU on the ADE20K semantic segmentation task, surpassing previous state-of-the-art Swin Transformer backbone by +1.2, +2.0, +1.4, and +2.0 respectively under the similar FLOPs setting. By further pretraining on the larger dataset ImageNet-21K, we achieve 87.5% Top-1 accuracy on ImageNet-1K and high segmentation performance on ADE20K with 55.7 mIoU. The code and models are available at https://github.com/microsoft/CSWin-Transformer.

PaperPDFConference PDFCodeCode 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

Syntology 6 code samples harvested from 2 repositories linked to this paper: 4 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; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 2 ran (0 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

microsoft/CSWin-Transformer officialmentioned in papermentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
TJUdyk/CSWin-Transformer mentioned on GitHubpytorchMITSyntology: not harvested report
fogfog2/packnet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method. report
lyqcom/cswin-transformer mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
BR-IDL/PaddleViT paddleSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
gitlab.com/birder/birder pytorchSyntology: 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

6 samples harvested: 4 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; 2 where Syntology's instrument failed) · 2 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
1ran; the contract check could not run
2ran
2unverified

Licence: 0 of the 6 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.

microsoft/CSWin-Transformer official repository 4 samples, 2 ran (0 instrument-failed) · 2 unverified
create_optimizer in 37 papers finetune.py ran MIT (permissive) · 3b22aba5effad739 · report fixture: signature args:Args/0/?, parameters:generator/0/?, filter_bias_and_bn:bool/0/bool · returned AdamW · level recorded 2026-09-25
load_img in 47 papers labeled_memcached_dataset.py ran MIT (permissive) · 4d0c2350b24a4430 · report fixture: signature filepath:str/0/str · returned Image · level recorded 2026-09-26
train_epoch in 71 papers finetune.py unverified MIT (permissive) · e3b8df6691b9c559 · report
validate in 313 papers finetune.py unverified MIT (permissive) · e2a98c6a53ded11f · report
lyqcom/cswin-transformer community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
img2windows in 15 papers models/cswin.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 39b18f062e0cc6d9 · report fixture: signature img:Tensor/4/float, H_sp:int/0/int, W_sp:int/0/int · returned Tensor · level recorded 2026-09-22
windows2img in 15 papers models/cswin.py ran · our draft was wrong MIT (permissive) · ab01fbfe58c75b08 · report fixture: signature img_splits_hw:Tensor/4/float, H_sp:int/0/int, W_sp:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22

Tasks

Image ClassificationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet CSWin-L (384 res,ImageNet-22k pretrain) GFLOPs 96.8 #84 of 1060 Archive leaderboard report
Image Classification ImageNet CSWin-L (384 res,ImageNet-22k pretrain) Number of params 173M #84 of 1060 Archive leaderboard report
Image Classification ImageNet CSWin-L (384 res,ImageNet-22k pretrain) Top 1 Accuracy 87.5% #84 of 1060 Archive leaderboard report
Semantic Segmentation ADE20K CSWin-L (UperNet, ImageNet-22k pretrain) Validation mIoU 55.70 #45 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val CSWin-L (UperNet, ImageNet-22k pretrain) mIoU 55.7 #27 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 EncodingsAdamAttentionBPEDense 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