Methods › Computer Vision › Image Models › MetaFormer
MetaFormer
Introduced by Weihao Yu et al. in MetaFormer Is Actually What You Need for Vision
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
MetaFormer is a general architecture abstracted from Transformers by not specifying the token mixer.
In Syntology about another paper, arXiv:2203.02751: harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2203.02751'). Repositories: 2 listed of 2 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2203.02751, not a method entry. About another paper: this answer is about arXiv:2203.02751, while the archive credits arXiv:2111.11418.
Origin paper of this answer, arXiv:2203.02751 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 14 harvested samples) · 3 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 20 · with a code link: 11 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 20 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 20 of 20, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
EMF: Event Meta Formers for Event-based Real-time Traffic Object Detection 5 Apr 2025 · 0 repositories · arXiv:2504.04124
-
Foundation Models For Seismic Data Processing: An Extensive Review 31 Mar 2025 · 1 repository · arXiv:2503.24166
-
SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks 9 Mar 2025 · 0 repositories · arXiv:2503.08703
-
Static Key Attention in Vision 9 Dec 2024 · 0 repositories · arXiv:2412.07049
-
Aberration Correcting Vision Transformers for High-Fidelity Metalens Imaging 5 Dec 2024 · 0 repositories · arXiv:2412.04591
-
MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers 28 Nov 2024 · 0 repositories · arXiv:2411.18995
-
MetaFormer and CNN Hybrid Model for Polyp Image Segmentation 16 Sep 2024 · 1 repository
-
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation 14 Aug 2024 · 1 repository · arXiv:2408.07576
-
ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding 22 Mar 2024 · 0 repositories · arXiv:2403.15004
-
HyenaPixel: Global Image Context with Convolutions 29 Feb 2024 · 1 repository · arXiv:2402.19305
-
Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making 4 Oct 2023 · 0 repositories · arXiv:2310.03022
-
SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation 22 Aug 2023 · 1 repository · arXiv:2308.11568
-
Pretraining is All You Need: A Multi-Atlas Enhanced Transformer Framework for Autism Spectrum Disorder Classification 4 Jul 2023 · 1 repository · arXiv:2307.01759
-
M^2UNet: MetaFormer Multi-scale Upsampling Network for Polyp Segmentation 14 Jun 2023 · 0 repositories · arXiv:2306.08600
-
A Mask Free Neural Network for Monaural Speech Enhancement 7 Jun 2023 · 2 repositories · arXiv:2306.04286Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
DeformableFormer: Classification of Endoscopic Ultrasound Guided Fine Needle Biopsy in Pancreatic Diseases 21 Apr 2023 · 0 repositories · arXiv:2304.10791
-
FFT-based Dynamic Token Mixer for Vision 7 Mar 2023 · 1 repository · arXiv:2303.03932
-
MetaFormer Baselines for Vision 24 Oct 2022 · 8 repositories · arXiv:2210.13452Syntology community repositories only · 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 (of 4 harvested samples)
-
MetaFormer: A Unified Meta Framework for Fine-Grained Recognition 5 Mar 2022 · 2 repositories · arXiv:2203.02751Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 14 harvested samples) · 3 pointer-only (licence)
-
MetaFormer Is Actually What You Need for Vision 22 Nov 2021 · 18 repositories · arXiv:2111.11418Syntology community repositories only · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 31 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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