Papers › Going deeper with Image Transformers

Going deeper with Image Transformers

31 Mar 2021ICCV 2021 10arXiv:2103.17239archive 2025-07-28

Hugo Touvron, Matthieu Cord, Alexandre Sablayrolles, Gabriel Synnaeve, Hervé Jégou

Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such dedicated transformers. We make two transformers architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current SOTA with less FLOPs and parameters. Moreover, our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models.

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

No sample from the archive's official repositories (rwightman/pytorch-image-models, facebookresearch/deit) is linked to this paper; the 9 samples below come from 4 community repositories, and 2 more are identical to code Syntology harvested from another paper's repository. Syntology harvested code from rwightman/pytorch-image-models for another paper; from facebookresearch/deit for 2 other papers.

rwightman/pytorch-image-models: Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. facebookresearch/deit: Syntology's graph links these samples to Augmenting Convolutional networks with attention-based aggregation (arXiv:2112.13692; that paper's own run record: 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) and Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples: 9 from 4 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 11: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 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: community (archive-listed): 9 samples from 4 repositories, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 9 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 9 samples that ran have no recorded date.

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

rwightman/pytorch-image-models officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
facebookresearch/deit officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Augmenting Convolutional networks with attention-based aggregation (arXiv:2112.13692; that paper's own run record: 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) and Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
CPones/Paddle_CaiT mentioned on GitHubpaddleApache-2.0Syntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
DarshanDeshpande/jax-models mentioned on GitHubjaxSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
IMvision12/keras-vision-models 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
ahmedelmahy/myownvit mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (arXiv:2101.11986; that paper's own run record: 21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified), CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification (arXiv:2103.14899; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 1 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified), CvT: Introducing Convolutions to Vision Transformers (arXiv:2103.15808; that paper's own run record: 39 ran (of which 19 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
conceptofmind/CaiT-Flax mentioned on GitHubjaxSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
holdfire/CLS mentioned on GitHubpytorchSyntology: not harvested report
holdfire/FAS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified) and 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
jaketae/res-mlp mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResMLP: Feedforward networks for image classification with data-efficient training (arXiv:2105.03404; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
liuxingwt/CLS mentioned on GitHubpytorchSyntology: not harvested report
lucidrains/vit-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified), Parameter Prediction for Unseen Deep Architectures (arXiv:2110.13100; that paper's own run record: 6 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; 5 where Syntology's instrument failed) · 1 unverified), SepViT: Separable Vision Transformer (arXiv:2203.15380; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
martinsbruveris/tensorflow-image-models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MLP-Mixer: An all-MLP Architecture for Vision (arXiv:2105.01601; that paper's own run record: 114 ran (of which 77 constructed an object rather than computing a result; 104 with no instrument failure: 2 honoured, 1 violated, 101 with no contract checked; 10 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
sayakpaul/cait-tf mentioned on GitHubtfApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ttt496/vit-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (arXiv:2101.11986; that paper's own run record: 21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified), Rethinking Spatial Dimensions of Vision Transformers (arXiv:2103.16302; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified) and LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference (arXiv:2104.01136; that paper's own run record: 23 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-4/Code8 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code7 mindsporeSyntology: not harvested report
BR-IDL/PaddleViT paddleSyntology: not harvested report
Mind23-2/MindCode-4 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code6 mindsporeSyntology: 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 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.

2ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
4ran
2unverified

Licence: 2 of the 11 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 4 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. 2 samples are listed last, in a group without a repository. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

CPones/Paddle_CaiT community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
get_args in 84 papers CaiT/infer.py ran Apache-2.0 (permissive) · 5fe12143b1680470 · report fixture: signature add_help:bool/0/bool · returned Namespace · level recorded 2026-09-24
get_exclude_from_weight_decay_fn CaiT/utils.py ran Apache-2.0 (permissive) · 7cdb59fd6a14bd54 · report fixture: signature exclude_list:list/1/str · returned function · level recorded 2026-09-24
get_config in 203 papers CaiT/config.py unverified Apache-2.0 (permissive) · 160fd4002bd2e51b · report
update_config in 54 papers CaiT/config.py unverified Apache-2.0 (permissive) · ee77e3fcb05ad040 · report
DarshanDeshpande/jax-models community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
jax_models/models/swin_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 07b1c6d8d9489187 · report fixture: signature x:ArrayImpl/4/float, window_size:int/0/int · returned ArrayImpl · level recorded, date not recorded
window_reverse in 296 papers jax_models/models/swin_transformer.py ran · our draft was wrong Apache-2.0 (permissive) · 0859cb39e97935ba · report fixture: signature windows:ArrayImpl/4/float, window_size:int/0/int, height:int/0/int, width:int/0/int · returned ArrayImpl · level recorded, date not recorded
conceptofmind/CaiT-Flax community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
dropout_layers in 7 papers cait.py ran · our draft was wrong fingerprinted MIT (permissive) · 7794eb689431c216 · report fixture: signature layers:list/1/str, dropout:float/0/float · returned list · level recorded, date not recorded
sayakpaul/cait-tf community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
conv_transpose utils/helpers.py ran fingerprinted Apache-2.0 (permissive) · e218ba48c9d2c190 · report fixture: signature w:ndarray/4/float · returned ndarray · level recorded 2026-09-24
mlp in 108 papers cait/models.py ran Apache-2.0 (permissive) · ae83452001c08f2a · report fixture: signature x:KerasTensor/0/float, dropout_rate:float/0/float, hidden_units:list/1/int · returned KerasTensor · level recorded 2026-09-24
Repository not located 2 samples, 2 ran (0 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
repository not located ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
pair in 101 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 6ba8cee9f5daea41 · report fixture: signature t:int/0/int · returned tuple · level recorded, date not recorded

Tasks

Image ClassificationTransfer Learningimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 CaiT-M-36 U 224 Percentage correct 99.4 #5 of 265 Archive leaderboard report
Image Classification CIFAR-100 CaiT-M-36 U 224 Percentage correct 93.1 #10 of 211 Archive leaderboard report
Image Classification Flowers-102 CaiT-M-36 U 224 Accuracy 99.1 #16 of 52 Archive leaderboard report
Image Classification ImageNet CaiT-M-48-448 GFLOPs 377.3 #140 of 1060 Archive leaderboard report
Image Classification ImageNet CaiT-M-48-448 Number of params 438M #140 of 1060 Archive leaderboard report
Image Classification ImageNet CaiT-M-48-448 Top 1 Accuracy 86.5% #140 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M36-448 GFLOPs 247.8 #162 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M36-448 Number of params 271M #162 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M36-448 Top 1 Accuracy 86.3% #162 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M-36 GFLOPs 173.3 #174 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M-36 Number of params 270.9M #174 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M-36 Top 1 Accuracy 86.1% #174 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M-24 GFLOPs 116.1 #196 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M-24 Number of params 185.9M #196 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-M-24 Top 1 Accuracy 85.8% #196 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-36 GFLOPs 48 #234 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-36 Number of params 68.2M #234 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-36 Top 1 Accuracy 85.4% #234 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-48 GFLOPs 63.8 #241 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-48 Number of params 89.5M #241 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-48 Top 1 Accuracy 85.3% #241 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-24 GFLOPs 32.2 #257 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-24 Number of params 46.9M #257 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-S-24 Top 1 Accuracy 85.1% #257 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XS-36 GFLOPs 28.8 #285 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XS-36 Number of params 38.6M #285 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XS-36 Top 1 Accuracy 84.8% #285 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XS-24 GFLOPs 19.3 #354 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XS-24 Number of params 26.6M #354 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XS-24 Top 1 Accuracy 84.1% #354 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XXS-36 GFLOPs 14.3 #559 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XXS-36 Number of params 17.3M #559 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XXS-36 Top 1 Accuracy 82.2% #559 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XXS-24 GFLOPs 9.6 #674 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XXS-24 Number of params 12M #674 of 1060 Archive leaderboard report
Image Classification ImageNet CAIT-XXS-24 Top 1 Accuracy 80.9% #674 of 1060 Archive leaderboard report
Image Classification ImageNet ReaL CAIT-M36-448 Accuracy 90.2% #19 of 57 Archive leaderboard report
Image Classification ImageNet V2 CAIT-M36-448 Top 1 Accuracy 76.7 #16 of 33 Archive leaderboard report
Image Classification Stanford Cars CaiT-M-36 U 224 Accuracy 94.2 #5 of 24 Archive leaderboard report
Image Classification iNaturalist 2018 CaiT-M-36 U 224 Top-1 Accuracy 78% #22 of 60 Archive leaderboard report
Image Classification iNaturalist 2019 CaiT-M-36 U 224 Top-1 Accuracy 81.8 #10 of 22 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: Class Attention, LayerScale

AttentionCaiTClass AttentionDeiTDense ConnectionsFeedforward NetworkLayer NormalizationLayerScaleLinear LayerMulti-Head AttentionResidual ConnectionSoftmax

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