Papers › MetaFormer Baselines for Vision

MetaFormer Baselines for Vision

24 Oct 2022arXiv:2210.13452archive 2025-07-28

Weihao Yu, Chenyang Si, Pan Zhou, Mi Luo, Yichen Zhou, Jiashi Feng, Shuicheng Yan, Xinchao Wang

MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, without focusing on token mixer design: we introduce several baseline models under MetaFormer using the most basic or common mixers, and summarize our observations as follows: (1) MetaFormer ensures solid lower bound of performance. By merely adopting identity mapping as the token mixer, the MetaFormer model, termed IdentityFormer, achieves >80% accuracy on ImageNet-1K. (2) MetaFormer works well with arbitrary token mixers. When specifying the token mixer as even a random matrix to mix tokens, the resulting model RandFormer yields an accuracy of >81%, outperforming IdentityFormer. Rest assured of MetaFormer's results when new token mixers are adopted. (3) MetaFormer effortlessly offers state-of-the-art results. With just conventional token mixers dated back five years ago, the models instantiated from MetaFormer already beat state of the art. (a) ConvFormer outperforms ConvNeXt. Taking the common depthwise separable convolutions as the token mixer, the model termed ConvFormer, which can be regarded as pure CNNs, outperforms the strong CNN model ConvNeXt. (b) CAFormer sets new record on ImageNet-1K. By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85.5% at 224x224 resolution, under normal supervised training without external data or distillation. In our expedition to probe MetaFormer, we also find that a new activation, StarReLU, reduces 71% FLOPs of activation compared with GELU yet achieves better performance. We expect StarReLU to find great potential in MetaFormer-like models alongside other neural networks.

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

No sample from the archive's official repositories (rwightman/pytorch-image-models, sail-sg/metaformer) is linked to this paper; the 4 samples below come from 1 community repository. Syntology harvested code from rwightman/pytorch-image-models for another paper; sail-sg/metaformer was not harvested.

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.

Syntology 4 code samples harvested from 1 repository linked to this paper: 1 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; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 4 samples 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 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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
sail-sg/metaformer officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Westlake-AI/MogaNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MogaNet: Multi-order Gated Aggregation Network (arXiv:2211.03295; that paper's own run record: 12 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Westlake-AI/openmixup mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 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; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
sail-sg/poolformer mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
facebookresearch/xformers pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Longformer: The Long-Document Transformer (arXiv:2004.05150; that paper's own run record: 22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified) and Self-attention Does Not Need O(n²) Memory (arXiv:2112.05682; that paper's own run record: 33 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 6 violated, 12 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. 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

4 samples harvested: 1 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; 0 where Syntology's instrument failed) · 3 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
3unverified

Licence: 0 of the 4 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 sail-sg/poolformer. “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.

sail-sg/poolformer community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
reshape_transform_resmlp misc/cam_image.py ran Apache-2.0 (permissive) · b84f022af3d984dc · report fixture: signature tensor:Tensor/3/float, height:int/0/int, width:int/0/int · returned Tensor · level recorded 2026-09-25
basic_blocks models/poolformer.py unverified Apache-2.0 (permissive) · 4dbed9d1ded8239d · report
reshape_transform_swin misc/cam_image.py unverified Apache-2.0 (permissive) · 145f9f895f57722f · report
reshape_transform_vit misc/cam_image.py unverified Apache-2.0 (permissive) · 9b13f431e8787323 · report

Tasks

Domain GeneralizationImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A CAFormer-B36 (IN-21K, 384) Number of params 99M #5 of 39 Archive leaderboard report
Domain Generalization ImageNet-A CAFormer-B36 (IN-21K, 384) Top-1 accuracy % 79.5 #5 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 (IN-21K, 384) Number of params 100M #8 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 (IN-21K, 384) Top-1 accuracy % 73.5 #8 of 39 Archive leaderboard report
Domain Generalization ImageNet-A CAFormer-B36 (IN-21K) Number of params 99M #9 of 39 Archive leaderboard report
Domain Generalization ImageNet-A CAFormer-B36 (IN-21K) Top-1 accuracy % 69.4 #9 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 (IN-21K) Number of params 100M #12 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 (IN-21K) Top-1 accuracy % 63.3 #12 of 39 Archive leaderboard report
Domain Generalization ImageNet-A CAFormer-B36 (384) Number of params 99M #14 of 39 Archive leaderboard report
Domain Generalization ImageNet-A CAFormer-B36 (384) Top-1 accuracy % 61.9 #14 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 (384) Number of params 100M #17 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 (384) Top-1 accuracy % 55.3 #17 of 39 Archive leaderboard report
Domain Generalization ImageNet-A CAFormer-B36 Number of params 99M #20 of 39 Archive leaderboard report
Domain Generalization ImageNet-A CAFormer-B36 Top-1 accuracy % 48.5 #20 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 Number of params 100M #23 of 39 Archive leaderboard report
Domain Generalization ImageNet-A ConvFormer-B36 Top-1 accuracy % 40.1 #23 of 39 Archive leaderboard report
Domain Generalization ImageNet-C CAFormer-B36 (IN21K, 384) Number of params 99M #2 of 47 Archive leaderboard report
Domain Generalization ImageNet-C CAFormer-B36 (IN21K, 384) mean Corruption Error (mCE) 30.8 #2 of 47 Archive leaderboard report
Domain Generalization ImageNet-C CAFormer-B36 (IN21K) mean Corruption Error (mCE) 31.8 #5 of 47 Archive leaderboard report
Domain Generalization ImageNet-C ConvFormer-B36 (IN21K) mean Corruption Error (mCE) 35.0 #7 of 47 Archive leaderboard report
Domain Generalization ImageNet-C CAFormer-B36 mean Corruption Error (mCE) 42.6 #18 of 47 Archive leaderboard report
Domain Generalization ImageNet-C ConvFormer-B36 mean Corruption Error (mCE) 46.3 #23 of 47 Archive leaderboard report
Domain Generalization ImageNet-R CAFormer-B36 (IN21K, 384) Top-1 Error Rate 29.6 #5 of 39 Archive leaderboard report
Domain Generalization ImageNet-R CAFormer-B36 (IN21K) Top-1 Error Rate 31.7 #7 of 39 Archive leaderboard report
Domain Generalization ImageNet-R ConvFormer-B36 (IN21K, 384) Top-1 Error Rate 33.5 #11 of 39 Archive leaderboard report
Domain Generalization ImageNet-R ConvFormer-B36 (IN21K) Top-1 Error Rate 34.7 #13 of 39 Archive leaderboard report
Domain Generalization ImageNet-R CAFormer-B36 (384) Top-1 Error Rate 45 #21 of 39 Archive leaderboard report
Domain Generalization ImageNet-R CAFormer-B36 Top-1 Error Rate 46.1 #23 of 39 Archive leaderboard report
Domain Generalization ImageNet-R ConvFormer-B36 (384) Top-1 Error Rate 47.8 #24 of 39 Archive leaderboard report
Domain Generalization ImageNet-R ConvFormer-B36 Top-1 Error Rate 48.9 #25 of 39 Archive leaderboard report
Domain Generalization ImageNet-Sketch CAFormer-B36 (IN21K, 384) Top-1 accuracy 54.5 #5 of 20 Archive leaderboard report
Domain Generalization ImageNet-Sketch ConvFormer-B36 (IN21K, 384) Top-1 accuracy 52.9 #7 of 20 Archive leaderboard report
Domain Generalization ImageNet-Sketch CAFormer-B36 (IN21K) Top-1 accuracy 52.8 #8 of 20 Archive leaderboard report
Domain Generalization ImageNet-Sketch ConvFormer-B36 (IN21K) Top-1 accuracy 52.7 #9 of 20 Archive leaderboard report
Domain Generalization ImageNet-Sketch CAFormer-B36 Top-1 accuracy 42.5 #17 of 20 Archive leaderboard report
Domain Generalization ImageNet-Sketch ConvFormer-B36 Top-1 accuracy 39.5 #19 of 20 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (384 res, 21K) GFLOPs 72.2 #59 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (384 res, 21K) Number of params 99M #59 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (384 res, 21K) Top 1 Accuracy 88.1% #59 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (384 res, 21K) GFLOPs 66.5 #79 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (384 res, 21K) Number of params 100M #79 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (384 res, 21K) Top 1 Accuracy 87.6% #79 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (384 res, 21K) GFLOPs 42 #83 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (384 res, 21K) Number of params 56M #83 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (384 res, 21K) Top 1 Accuracy 87.5% #83 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (224 res, 21K) GFLOPs 23.2 #93 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (224 res, 21K) Number of params 99M #93 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (224 res, 21K) Top 1 Accuracy 87.4% #93 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (224 res, 21K) GFLOPs 22.6 #113 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (224 res, 21K) Number of params 100M #113 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (224 res, 21K) Top 1 Accuracy 87.0% #113 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (384 res, 21K) GFLOPs 26.0 #116 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (384 res, 21K) Number of params 39M #116 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (384 res, 21K) Top 1 Accuracy 86.9% #116 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (384 res, 21K) GFLOPs 37.7 #117 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (384 res, 21K) Number of params 57M #117 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (384 res, 21K) Top 1 Accuracy 86.9% #117 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (224 res, 21K) GFLOPs 13.2 #132 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (224 res, 21K) Number of params 56M #132 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (224 res, 21K) Top 1 Accuracy 86.6% #132 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (384 res, 21K) GFLOPs 22.4 #147 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (384 res, 21K) Number of params 40M #147 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (384 res, 21K) Top 1 Accuracy 86.4% #147 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (384 res) GFLOPs 72.2 #150 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (384 res) Number of params 99M #150 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (384 res) Top 1 Accuracy 86.4% #150 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (384 res) GFLOPs 42.0 #168 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (384 res) Number of params 56M #168 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (384 res) Top 1 Accuracy 86.2% #168 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (224 res, 21K) GFLOPs 12.8 #173 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (224 res, 21K) Number of params 57M #173 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (224 res, 21K) Top 1 Accuracy 86.1% #173 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (224 res, 21K) GFLOPs 8.0 #192 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (224 res, 21K) Number of params 39M #192 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (224 res, 21K) Top 1 Accuracy 85.8% #192 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (384 res) GFLOPs 26.0 #209 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (384 res) Number of params 39M #209 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (384 res) Top 1 Accuracy 85.7% #209 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (384 res) GFLOPs 66.5 #210 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (384 res) Number of params 100M #210 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (384 res) Top 1 Accuracy 85.7% #210 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (384 res) GFLOPs 37.7 #214 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (384 res) Number of params 57M #214 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (384 res) Top 1 Accuracy 85.6% #214 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (224 res) GFLOPs 23.2 #225 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (224 res) Number of params 99M #225 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-B36 (224 res) Top 1 Accuracy 85.5% #225 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (384 res, 21K) GFLOPs 13.4 #231 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (384 res, 21K) Number of params 26M #231 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (384 res, 21K) Top 1 Accuracy 85.4% #231 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (224 res, 21K) GFLOPs 7.6 #232 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (224 res, 21K) Number of params 40M #232 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (224 res, 21K) Top 1 Accuracy 85.4% #232 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (384 res) GFLOPs 22.4 #233 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (384 res) Number of params 40M #233 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (384 res) Top 1 Accuracy 85.4% #233 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (224 res) GFLOPs 13.2 #248 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (224 res) Number of params 56M #248 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-M36 (224 res) Top 1 Accuracy 85.2% #248 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (384 res) GFLOPs 13.4 #267 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (384 res) Number of params 26M #267 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (384 res) Top 1 Accuracy 85.0% #267 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (384 res, 21K) GFLOPs 11.6 #268 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (384 res, 21K) Number of params 27M #268 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (384 res, 21K) Top 1 Accuracy 85.0% #268 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (224 res) GFLOPs 22.6 #291 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (224 res) Number of params 100M #291 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-B36 (224 res) Top 1 Accuracy 84.8% #291 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (224 res) GFLOPs 8.0 #309 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (224 res) Number of params 39M #309 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S36 (224 res) Top 1 Accuracy 84.5% #309 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (224 res) GFLOPs 12.8 #311 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (224 res) Number of params 57M #311 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-M36 (224 res) Top 1 Accuracy 84.5% #311 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (384 res) GFLOPs 11.6 #318 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (384 res) Number of params 27M #318 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (384 res) Top 1 Accuracy 84.4% #318 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (224 res, 21K) GFLOPs 4.1 #353 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (224 res, 21K) Number of params 26M #353 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (224 res, 21K) Top 1 Accuracy 84.1% #353 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (224 res) GFLOPs 7.6 #355 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (224 res) Number of params 40M #355 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S36 (224 res) Top 1 Accuracy 84.1% #355 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (224 res, 21K) GFLOPs 3.9 #394 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (224 res, 21K) Number of params 27M #394 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (224 res, 21K) Top 1 Accuracy 83.7% #394 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (224 res) GFLOPs 4.1 #412 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (224 res) Number of params 26M #412 of 1060 Archive leaderboard report
Image Classification ImageNet CAFormer-S18 (224 res) Top 1 Accuracy 83.6% #412 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (224 res) GFLOPs 3.9 #478 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (224 res) Number of params 27M #478 of 1060 Archive leaderboard report
Image Classification ImageNet ConvFormer-S18 (224 res) Top 1 Accuracy 83.0% #478 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: StarReLU

AdamAttentionConvNeXtDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMetaFormerMulti-Head AttentionPoolFormerPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStarReLUTransformer

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