Papers › SimMIM: A Simple Framework for Masked Image Modeling

SimMIM: A Simple Framework for Masked Image Modeling

18 Nov 2021CVPR 2022 1arXiv:2111.09886archive 2025-07-28

Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu

This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let the masked image modeling task learn good representations, we systematically study the major components in our framework, and find that simple designs of each component have revealed very strong representation learning performance: 1) random masking of the input image with a moderately large masked patch size (e.g., 32) makes a strong pre-text task; 2) predicting raw pixels of RGB values by direct regression performs no worse than the patch classification approaches with complex designs; 3) the prediction head can be as light as a linear layer, with no worse performance than heavier ones. Using ViT-B, our approach achieves 83.8% top-1 fine-tuning accuracy on ImageNet-1K by pre-training also on this dataset, surpassing previous best approach by +0.6%. When applied on a larger model of about 650 million parameters, SwinV2-H, it achieves 87.1% top-1 accuracy on ImageNet-1K using only ImageNet-1K data. We also leverage this approach to facilitate the training of a 3B model (SwinV2-G), that by 40× less data than that in previous practice, we achieve the state-of-the-art on four representative vision benchmarks. The code and models will be publicly available at https://github.com/microsoft/SimMIM.

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="2111.09886")

Code

Syntology Ran 9 of 14 code samples harvested from 3 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 13 samples from 2 repositories, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/simmim officialmentioned in papermentioned on GitHubpytorchMIT report
Westlake-AI/openmixup mentioned on GitHubpytorch report
impiga/plain-detr mentioned on GitHubpytorch report
isaaccorley/hydro-foundation-model mentioned on GitHubpytorch report
lightly-ai/lightly 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

14 samples harvested; 9 ran; 0 honoured the contract we drafted; 5 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 · our draft was wrong
8ran
5unverified

Licence: 0 of the 14 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.

SimMIM microsoft/simmim/models/simmim.py official repository ran · metamorphic tier: deterministic MIT (permissive) · fddc32909150f889 · report
GlobalAttention impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · b0e55e16e4ab4b04 · report
LayerNormFP32 impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) ran fingerprinted MIT (permissive) · 6d0ff69e341e91b6 · report
LinearFP32 impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · ef982aba178be7dd · report
PatchEmbed impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 804ddd3c6093f073 · report
PatchMerging impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · a5518beb9daf7d60 · report
SimMIM Hazqeel09/ellzaf_ml/ellzaf_ml/models/simmim.py community (archive-listed) ran MIT (permissive) · 9ce7427c4503c13e · report
WindowAttention impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 5eec152e243ad651 · report
custom_normalize impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 4e2c8a04e709451b · report
BasicLayer impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) unverified MIT (permissive) · 590e8cc54154effc · report
SwinTransformerBlock impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) unverified MIT (permissive) · bcf8d3634776d004 · report
SwinTransformerGlobalBlock impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) unverified MIT (permissive) · deaa894233f1e3da · report
SwinTransformerV2 impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) unverified MIT (permissive) · d346a9e5a95c653f · report
load_swinv2_checkpoint impiga/plain-detr/models/swin_transformer_v2.py community (archive-listed) unverified MIT (permissive) · 6feca106254274b3 · report

Tasks

Representation LearningSelf-Supervised Image ClassificationTask 2

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (SwinV2-H, 512) Number of Params 658M #10 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (SwinV2-H, 512) Top 1 Accuracy 87.1% #10 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (Swin-L) Number of Params 197M #24 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (Swin-L) Top 1 Accuracy 85.4% #24 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (Swin-B) Number of Params 88M #38 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (Swin-B) Top 1 Accuracy 84.0% #38 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (ViT-B/16) Number of Params 85M #43 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimMIM (ViT-B/16) Top 1 Accuracy 83.8% #43 of 65 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.

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