Papers › MixFormer: Mixing Features across Windows and Dimensions

MixFormer: Mixing Features across Windows and Dimensions

6 Apr 2022CVPR 2022 1arXiv:2204.02557archive 2025-07-28

Qiang Chen, Qiman Wu, Jian Wang, Qinghao Hu, Tao Hu, Errui Ding, Jian Cheng, Jingdong Wang

While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a solution. First, we combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields. Second, we propose bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions. These two designs are integrated to achieve efficient feature mixing among windows and dimensions. Our MixFormer provides competitive results on image classification with EfficientNet and shows better results than RegNet and Swin Transformer. Performance in downstream tasks outperforms its alternatives by significant margins with less computational costs in 5 dense prediction tasks on MS COCO, ADE20k, and LVIS. Code is available at \url{https://github.com/PaddlePaddle/PaddleClas}.

PaperPDFConference PDFCodeCode 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="2204.02557")

Code

Syntology Ran 5 of 14 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: community (archive-listed): 14 samples from 2 repositories, 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.

PaddlePaddle/PaddleClas officialmentioned in papermentioned on GitHubpaddleApache-2.0 report
clearlon/stylemixformer mentioned on GitHubpytorch report
flytocc/PaddleClas mentioned on GitHubpaddleApache-2.0 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

14 samples harvested; 5 ran; 0 honoured the contract we drafted; 9 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.

5ran
9unverified

Licence: 0 of the 14 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; each sample names its own and says which. “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.

AttentionCC clearlon/stylemixformer/styleformer/archs/styleformer_util.py community (archive-listed) ran Apache-2.0 (permissive) · 5d037926d5843004 · report
ChannelInteraction clearlon/stylemixformer/styleformer/archs/styleformer_util.py community (archive-listed) ran Apache-2.0 (permissive) · 5e935e13456b2294 · report
MixRestormer clearlon/stylemixformer/styleformer/archs/styleformer_util.py community (archive-listed) ran Apache-2.0 (permissive) · 05212f4e91896ff3 · report
SimpleGate clearlon/stylemixformer/styleformer/archs/styleformer_util.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · abc6ee09587fed69 · report
SpatialInteraction clearlon/stylemixformer/styleformer/archs/styleformer_util.py community (archive-listed) ran Apache-2.0 (permissive) · f21f09acc77e8d76 · report
check_model_file flytocc/PaddleClas/paddleclas.py community (archive-listed) unverified Apache-2.0 (permissive) · fab16299446cee0f · report
cosine_similarity flytocc/PaddleClas/ppcls/loss/dist_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · bffab447a4eca741 · report
extract flytocc/PaddleClas/test_tipc/extract_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · efe80a6faca7b66d · report
inter_class_relation flytocc/PaddleClas/ppcls/loss/dist_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 58f2b08eed947b76 · report
is_valid flytocc/PaddleClas/test_tipc/extract_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · 413184c918d844c8 · report
pearson_correlation flytocc/PaddleClas/ppcls/loss/dist_loss.py community (archive-listed) unverified Apache-2.0 (permissive) · a7997903cea7558c · report
rerange_index flytocc/PaddleClas/ppcls/loss/comfunc.py community (archive-listed) unverified Apache-2.0 (permissive) · 21421188135068e9 · report
similar_model_names flytocc/PaddleClas/paddleclas.py community (archive-listed) unverified Apache-2.0 (permissive) · 398221cc3d60f209 · report
unique_shape flytocc/PaddleClas/ppcls/loss/afdloss.py community (archive-listed) unverified Apache-2.0 (permissive) · 0c3f60f3f5d20da9 · report

Tasks

Image Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionAverage PoolingBPEBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutInverted Residual BlockLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPointwise ConvolutionPosition-Wise Feed-Forward LayerRMSPropReLUResidual ConnectionSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockStochastic 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