Papers › Augmenting Convolutional networks with attention-based aggregation

Augmenting Convolutional networks with attention-based aggregation

27 Dec 2021arXiv:2112.13692archive 2025-07-28

Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, Piotr Bojanowski, Armand Joulin, Gabriel Synnaeve, Hervé Jégou

We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning. We replace the final average pooling by an attention-based aggregation layer akin to a single transformer block, that weights how the patches are involved in the classification decision. We plug this learned aggregation layer with a simplistic patch-based convolutional network parametrized by 2 parameters (width and depth). In contrast with a pyramidal design, this architecture family maintains the input patch resolution across all the layers. It yields surprisingly competitive trade-offs between accuracy and complexity, in particular in terms of memory consumption, as shown by our experiments on various computer vision tasks: object classification, image segmentation and detection.

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

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

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 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.

No sample is linked to this paper from 2 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.

facebookresearch/deit officialmentioned in paperpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
DarshanDeshpande/jax-models mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Networks with Stochastic Depth (arXiv:1603.09382; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (arXiv:2102.12122; that paper's own run record: 22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified), 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) and 5 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
dongkyuk/PatchConvNet-pytorch mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
keras-team/keras-io tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Forward-Forward Algorithm: Some Preliminary Investigations (arXiv:2212.13345; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/External-Attention-MindSpore 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

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 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

Licence: 0 of the 2 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.

facebookresearch/deit official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
conv3x3 in 1,376 papers patchconvnet_models.py ran · our draft was wrong Apache-2.0 (permissive) · ba6aa5f07daca9cd · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
dongkyuk/PatchConvNet-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_activation in 218 papers model/custom_blocks.py ran MIT (permissive) · af6a4caff0775c04 · report fixture: signature act:str/0/str · returned ReLU · level recorded 2026-09-24

Tasks

ClassificationImage ClassificationImage SegmentationObject DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet PatchConvNet-L120-21k-384 Number of params 334.3M #108 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-L120-21k-384 Top 1 Accuracy 87.1% #108 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-B60-21k-384 Number of params 99.4M #139 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-B60-21k-384 Top 1 Accuracy 86.5% #139 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-S60-21k-512 Number of params 25.2M #230 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-S60-21k-512 Top 1 Accuracy 85.4% #230 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-B120 Number of params 188.6M #360 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-B120 Top 1 Accuracy 84.1% #360 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-B60 Number of params 99.4M #423 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-B60 Top 1 Accuracy 83.5% #423 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-S120 Number of params 47.7M #458 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-S120 Top 1 Accuracy 83.2% #458 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-S60 Number of params 25.2M #574 of 1060 Archive leaderboard report
Image Classification ImageNet PatchConvNet-S60 Top 1 Accuracy 82.1% #574 of 1060 Archive leaderboard report
Object Detection COCO minival PatchConvNet-S120 (Mask R-CNN) box AP 47.0 #100 of 220 Archive leaderboard report
Object Detection COCO minival PatchConvNet-S60 (Mask R-CNN) box AP 46.4 #106 of 220 Archive leaderboard report
Semantic Segmentation ADE20K PatchConvNet-L120 (UperNet) Validation mIoU 52.9 #84 of 235 Archive leaderboard report
Semantic Segmentation ADE20K PatchConvNet-B120 (UperNet) Validation mIoU 52.8 #86 of 235 Archive leaderboard report
Semantic Segmentation ADE20K PatchConvNet-B60 (UperNet) Validation mIoU 51.1 #102 of 235 Archive leaderboard report
Semantic Segmentation ADE20K PatchConvNet-S60 (UperNet) Validation mIoU 49.3 #134 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val PatchConvNet-L120 (UperNet) mIoU 52.9 #41 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val PatchConvNet-B120 (UperNet) mIoU 52.8 #43 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val PatchConvNet-B60 (UperNet) mIoU 51.1 #47 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val PatchConvNet-S60 (UperNet) mIoU 49.3 #59 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

Average PoolingClass AttentionLayerScale

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