Papers › Visformer: The Vision-friendly Transformer

Visformer: The Vision-friendly Transformer

26 Apr 2021ICCV 2021 10arXiv:2104.12533archive 2025-07-28

Zhengsu Chen, Lingxi Xie, Jianwei Niu, Xuefeng Liu, Longhui Wei, Qi Tian

The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still growing number of evidences showing that these models suffer over-fitting especially when the training data is limited. This paper offers an empirical study by performing step-by-step operations to gradually transit a Transformer-based model to a convolution-based model. The results we obtain during the transition process deliver useful messages for improving visual recognition. Based on these observations, we propose a new architecture named Visformer, which is abbreviated from the `Vision-friendly Transformer'. With the same computational complexity, Visformer outperforms both the Transformer-based and convolution-based models in terms of ImageNet classification accuracy, and the advantage becomes more significant when the model complexity is lower or the training set is smaller. The code is available at https://github.com/danczs/Visformer.

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="2104.12533")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

danczs/Visformer officialmentioned in papermentioned on GitHubpytorch report
SforAiDl/vformer mentioned on GitHubpytorch report
rwightman/pytorch-image-models 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

1 sample harvested; 1 ran; 0 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.

1ran · fixture could not drive it

Licence: 1 of the 1 sample is 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 danczs/Visformer. “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.

drop_path danczs/Visformer/models.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 55120f2026b56aa2 · report

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet Visformer-S GFLOPs 4.9 #564 of 1060 Archive leaderboard report
Image Classification ImageNet Visformer-S Number of params 40.2M #564 of 1060 Archive leaderboard report
Image Classification ImageNet Visformer-S Top 1 Accuracy 82.2% #564 of 1060 Archive leaderboard report
Image Classification ImageNet Visformer-Ti GFLOPs 1.3 #821 of 1060 Archive leaderboard report
Image Classification ImageNet Visformer-Ti Number of params 10.3M #821 of 1060 Archive leaderboard report
Image Classification ImageNet Visformer-Ti Top 1 Accuracy 78.6% #821 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: Visformer

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionBPEBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGrouped ConvolutionLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerVisformer

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