Papers › Involution: Inverting the Inherence of Convolution for Visual Recognition

Involution: Inverting the Inherence of Convolution for Visual Recognition

10 Mar 2021CVPR 2021 1arXiv:2103.06255archive 2025-07-28

Duo Li, Jie Hu, Changhu Wang, Xiangtai Li, Qi She, Lei Zhu, Tong Zhang, Qifeng Chen

Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision. In this work, we rethink the inherent principles of standard convolution for vision tasks, specifically spatial-agnostic and channel-specific. Instead, we present a novel atomic operation for deep neural networks by inverting the aforementioned design principles of convolution, coined as involution. We additionally demystify the recent popular self-attention operator and subsume it into our involution family as an over-complicated instantiation. The proposed involution operator could be leveraged as fundamental bricks to build the new generation of neural networks for visual recognition, powering different deep learning models on several prevalent benchmarks, including ImageNet classification, COCO detection and segmentation, together with Cityscapes segmentation. Our involution-based models improve the performance of convolutional baselines using ResNet-50 by up to 1.6% top-1 accuracy, 2.5% and 2.4% bounding box AP, and 4.7% mean IoU absolutely while compressing the computational cost to 66%, 65%, 72%, and 57% on the above benchmarks, respectively. Code and pre-trained models for all the tasks are available at https://github.com/d-li14/involution.

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

The archive's official repository (d-li14/involution) was not harvested; the 9 samples below come from 7 community repositories.

Syntology 9 code samples harvested from 7 repositories linked to this paper: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 7 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 9 samples from 7 repositories, 7 ran (7 with no instrument failure; 0 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.

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

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

d-li14/involution officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
ChristophReich1996/Involution mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
PrivateMaRyan/keras-involution2D mentioned on GitHubtfSyntology: not harvested report
PrivateMaRyan/keras-involution2Ds mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
YashovardhanSrivastava19/Inv_Conv_Model mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
YirunKCL/Tensorflow-Keras-Involution2D mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ariG23498/involution-tf mentioned on GitHubtfSyntology: not harvested report
justanhduc/involution mentioned on GitHubpytorchSyntology: not harvested report
shikishima-TasakiLab/Involution-PyTorch mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
shuuchen/involution.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
xmu-xiaoma666/External-Attention-pytorch pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

9 samples harvested: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 7 samples that ran constructed an object rather than computing a result. “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.

7ran
2unverified

Licence: 4 of the 9 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 7 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 3 samples 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.

ChristophReich1996/Involution community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Involution2d involution/involution.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 56639e9724c537c5 · report fixture: returned Involution2d · level recorded 2026-09-22
PrivateMaRyan/keras-involution2Ds community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Involution2D Involution2D.py ran no licence file found · pointer only · b4e4c359cd255f73 · report fixture: returned Involution2D · level recorded 2026-09-22
YashovardhanSrivastava19/Inv_Conv_Model community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
InvolutionLayer InConvModel.py ran MIT (permissive) · c541633190c973cd · report fixture: returned InvolutionLayer · level recorded 2026-09-22
Configuration InConvModel.py unverified MIT (permissive) · 53278de7fe970d81 · report
YirunKCL/Tensorflow-Keras-Involution2D community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Involution2D involution2d.py ran no licence file found · pointer only · fab2bfdc9b7802ab · report fixture: returned Involution2D · level recorded 2026-09-22
shikishima-TasakiLab/Involution-PyTorch community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Involution2d involution/involution2d.py ran licence not identified · pointer only · 0fddcb87a4ff3ec5 · report fixture: returned Involution2d · level recorded 2026-09-22
_involution2d involution/involution2d.py unverified licence not identified · pointer only · 15063abf3990f72c · report
shuuchen/involution.pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Involution involution.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2ab588f06b5fcaf4 · report fixture: returned Involution · level recorded 2026-09-22
xmu-xiaoma666/External-Attention-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Involution model/conv/Involution.py ran fingerprinted MIT (permissive) · 7d4e496bf8ce2354 · report fixture: returned Involution · level recorded 2026-09-22

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.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Involution (graph method: Involution). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. Involution2D entry · level 1 · ran · fab2bfdc9b7802ab

harvested Assembly for Involution (graph method: Involution). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. Involution2d entry · level 1 · ran · 56639e9724c537c5

harvested Assembly for Involution (graph method: Involution). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. Involution entry · level 1 · ran · 2ab588f06b5fcaf4

harvested Assembly for Involution (graph method: Involution). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. Involution entry · level 1 · ran · 7d4e496bf8ce2354

harvested Assembly for Involution (graph method: Involution). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. Involution2D entry · level 1 · ran · b4e4c359cd255f73

harvested Assembly for Involution (graph method: Involution). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. Involution2d entry · level 1 · ran · 0fddcb87a4ff3ec5
  2. _involution2d helper · level 0 · unverified · 15063abf3990f72c

harvested Assembly for Involution (graph method: Involution). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 7 siblings

  1. InvolutionLayer entry · level 1 · ran · c541633190c973cd
  2. Configuration helper · level 0 · unverified · 53278de7fe970d81

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="2103.06255") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet RedNet-152 GFLOPs 6.8 #766 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-152 Number of params 34M #766 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-152 Top 1 Accuracy 79.3% #766 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-101 GFLOPs 4.7 #784 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-101 Number of params 25.6M #784 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-101 Top 1 Accuracy 79.1% #784 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-50 GFLOPs 2.7 #838 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-50 Number of params 15.5M #838 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-50 Top 1 Accuracy 78.4% #838 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-38 GFLOPs 2.2 #869 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-38 Number of params 12.4M #869 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-38 Top 1 Accuracy 77.6% #869 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-26 GFLOPs 1.7 #933 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-26 Number of params 9.2M #933 of 1060 Archive leaderboard report
Image Classification ImageNet RedNet-26 Top 1 Accuracy 75.9% #933 of 1060 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: Involution

ConvolutionInvolution

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