Papers › Patches Are All You Need?

Patches Are All You Need?

24 Jan 2022arXiv:2201.09792archive 2025-07-28

Asher Trockman, J. Zico Kolter

Although convolutional networks have been the dominant architecture for vision tasks for many years, recent experiments have shown that Transformer-based models, most notably the Vision Transformer (ViT), may exceed their performance in some settings. However, due to the quadratic runtime of the self-attention layers in Transformers, ViTs require the use of patch embeddings, which group together small regions of the image into single input features, in order to be applied to larger image sizes. This raises a question: Is the performance of ViTs due to the inherently-more-powerful Transformer architecture, or is it at least partly due to using patches as the input representation? In this paper, we present some evidence for the latter: specifically, we propose the ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in that it operates directly on patches as input, separates the mixing of spatial and channel dimensions, and maintains equal size and resolution throughout the network. In contrast, however, the ConvMixer uses only standard convolutions to achieve the mixing steps. Despite its simplicity, we show that the ConvMixer outperforms the ViT, MLP-Mixer, and some of their variants for similar parameter counts and data set sizes, in addition to outperforming classical vision models such as the ResNet. Our code is available at https://github.com/locuslab/convmixer.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2201.09792")

Code

Syntology Ran 8 of 8 code samples harvested from 3 repositories linked to this paper; 0 have no recorded run. Of those that ran: 5 ran · honoured contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 6 samples from 2 repositories, 6 ran; community (archive-listed): 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

locuslab/convmixer officialmentioned in paperpytorch report
tmp-iclr/convmixer officialmentioned in paperpytorchMIT report
Westlake-AI/openmixup mentioned on GitHubpytorch report
brohrer/sharpened-cosine-similarity mentioned on GitHubjaxMIT report
osiriszjq/impulse_init mentioned on GitHubpytorch 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

8 samples harvested; 8 ran; 5 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran · honoured contract
1ran · our draft was wrong
2ran

Licence: 0 of the 8 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

count_params tmp-iclr/convmixer/pytorch-image-models/benchmark.py official repository ran · honoured contract MIT (permissive) · 410bffb8a07b52e3 · report
ConvMixer locuslab/convmixer/convmixer.py official repository ran · our draft was wrong MIT (permissive) · a7690d61376264fc · report
checkpoint_metric tmp-iclr/convmixer/pytorch-image-models/avg_checkpoints.py official repository ran fingerprinted MIT (permissive) · 33bca8cbc866bf64 · report
cuda_timestamp tmp-iclr/convmixer/pytorch-image-models/benchmark.py official repository ran · honoured contract fingerprinted MIT (permissive) · 50d653ee6a59955c · report
map_mx_to_torch_model tmp-iclr/convmixer/pytorch-image-models/convert/convert_from_mxnet.py official repository ran fingerprinted MIT (permissive) · 5bed58ca17652913 · report
timestamp tmp-iclr/convmixer/pytorch-image-models/benchmark.py official repository ran · honoured contract fingerprinted MIT (permissive) · 475160c5a1a1225a · report
SpatialConv2d_Linear_init osiriszjq/impulse_init/convmixer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 0440e95034d883bd · report
SpatialConv2d_init osiriszjq/impulse_init/convmixer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · b04417d600247aaa · report

Tasks

AllImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 ConvMixer-256/16 Percentage correct 96.74 #101 of 265 Archive leaderboard report
Image Classification CIFAR-10 ConvMixer-256/8 Percentage correct 96.03 #123 of 265 Archive leaderboard report
Image Classification ImageNet ConvMixer-1536/20 Number of params 51.6M #566 of 1060 Archive leaderboard report
Image Classification ImageNet ConvMixer-1536/20 Top 1 Accuracy 82.20 #566 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

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionAverage PoolingBPEBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationLabel SmoothingLayer NormalizationLinear LayerMLP-MixerMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual BlockResidual ConnectionSoftmaxTransformerVision Transformer

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