Papers › Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer

Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer

7 Jun 2021arXiv:2106.03650archive 2025-07-28

Zilong Huang, Youcheng Ben, Guozhong Luo, Pei Cheng, Gang Yu, Bin Fu

Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code. Furthermore, the depth-wise convolution is introduced to complement the spatial shuffle for enhancing neighbor-window connections. The proposed architectures achieve excellent performance on a wide range of visual tasks including image-level classification, object detection, and semantic segmentation. Code will be released for reproduction.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2106.03650")

Code

Syntology Ran 5 of 12 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: community (archive-listed): 12 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mulinmeng/Shuffle-Transformer mentioned on GitHubpytorchMIT 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

12 samples harvested; 5 ran; 1 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
1ran · fixture could not drive it
2ran
7unverified

Licence: 0 of the 12 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 mulinmeng/Shuffle-Transformer. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

window_partition mulinmeng/Shuffle-Transformer/models/swin_transformer.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report
build_optimizer mulinmeng/Shuffle-Transformer/optimizer.py community (archive-listed) ran MIT (permissive) · e35a4b2e4114b1a5 · report
get_grad_norm mulinmeng/Shuffle-Transformer/utils.py community (archive-listed) ran · honoured contract MIT (permissive) · eec1e7cba51d5e8e · report
set_weight_decay mulinmeng/Shuffle-Transformer/optimizer.py community (archive-listed) ran MIT (permissive) · b33222a09fc93bec · report
window_reverse mulinmeng/Shuffle-Transformer/models/swin_transformer.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report
auto_resume_helper mulinmeng/Shuffle-Transformer/utils.py community (archive-listed) unverified MIT (permissive) · 0c32459bef92ff8c · report
build_model mulinmeng/Shuffle-Transformer/models/build.py community (archive-listed) unverified MIT (permissive) · 2448a1ccdc5ce4aa · report
build_scheduler mulinmeng/Shuffle-Transformer/lr_scheduler.py community (archive-listed) unverified MIT (permissive) · c02cc4e0b5720211 · report
check_keywords_in_name mulinmeng/Shuffle-Transformer/optimizer.py community (archive-listed) unverified MIT (permissive) · b0a5beb34716d5a6 · report
create_logger mulinmeng/Shuffle-Transformer/logger.py community (archive-listed) unverified MIT (permissive) · 80450600f7f09b0a · report
get_config mulinmeng/Shuffle-Transformer/config.py community (archive-listed) unverified MIT (permissive) · 02a9e80c2bb81815 · report
load_checkpoint mulinmeng/Shuffle-Transformer/utils.py community (archive-listed) unverified MIT (permissive) · 640408a0715e42c2 · report

Tasks

Image ClassificationObject DetectionSegmentationSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K UperNet Shuffle-B Validation mIoU 50.5 #111 of 235 Archive leaderboard report
Semantic Segmentation ADE20K UperNet Shuffle-T Validation mIoU 47.6 #161 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val UperNet Shuffle-B mIoU 50.5 #49 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val UperNet Shuffle-S mIoU 49.6 #57 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val UperNet Shuffle-T mIoU 47.6 #66 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

Introduced by this paper: Shuffle-T

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionShuffle-TSoftmaxTransformer

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