Papers › Better plain ViT baselines for ImageNet-1k

Better plain ViT baselines for ImageNet-1k

3 May 2022arXiv:2205.01580archive 2025-07-28

Lucas Beyer, Xiaohua Zhai, Alexander Kolesnikov

It is commonly accepted that the Vision Transformer model requires sophisticated regularization techniques to excel at ImageNet-1k scale data. Surprisingly, we find this is not the case and standard data augmentation is sufficient. This note presents a few minor modifications to the original Vision Transformer (ViT) vanilla training setting that dramatically improve the performance of plain ViT models. Notably, 90 epochs of training surpass 76% top-1 accuracy in under seven hours on a TPUv3-8, similar to the classic ResNet50 baseline, and 300 epochs of training reach 80% in less than one day.

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 repository (google-research/big_vision) is linked to this paper; the 22 samples below come from 3 community repositories, and 2 more are identical to code Syntology harvested from another paper's repository. Syntology harvested code from google-research/big_vision for 7 other papers.

google-research/big_vision: Syntology's graph links these samples to How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers (arXiv:2106.10270; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes (arXiv:2205.10337; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), PaLI: A Jointly-Scaled Multilingual Language-Image Model (arXiv:2209.06794; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified) and 4 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 24 code samples: 22 from 3 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 24: 23 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 22 samples from 3 repositories, 21 ran (18 with no instrument failure; 3 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 23 samples that ran have no recorded date.

google-research/big_vision officialmentioned in papermentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers (arXiv:2106.10270; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes (arXiv:2205.10337; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), PaLI: A Jointly-Scaled Multilingual Language-Image Model (arXiv:2209.06794; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified) and 4 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
conceptofmind/Simple-ViT-flax mentioned on GitHubjaxSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
jeongsoop/rgb-no-more mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
osiriszjq/impulse_init mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
yuyangshu/retinavit mentioned on GitHubjaxApache-2.0Syntology: 18 samples, 17 ran (1 instrument-failed) · 1 unverified report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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

24 samples harvested: 23 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 1 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.

5ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran; the contract check could not run
14ran
1unverified

Licence: 4 of the 24 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 2 samples are listed last, in a group without a repository. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

conceptofmind/Simple-ViT-flax community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
posemb_sincos_2d in 20 papers simple_vit.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · b848f8a0a583e58b · report fixture: signature patches:ArrayImpl/4/float, temperature:int/0/int · returned ArrayImpl · level recorded 2026-09-22
osiriszjq/impulse_init community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
SpatialConv2d_Linear_init convmixer.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · 0440e95034d883bd · report fixture: signature C:int/0/int, H:int/0/int, W:int/0/int, init:str/0/str · returned Tensor · level recorded 2026-09-22
SpatialConv2d_init convmixer.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · b04417d600247aaa · report fixture: signature C:int/0/int, kernel_size:int/0/int, init:str/0/str · returned Tensor · level recorded 2026-09-22
impulse_init vit.py ran; the contract check could not run (RAISES) MIT (permissive) · ce9f577538e842e0 · report fixture: returned tuple · level recorded 2026-09-22
yuyangshu/retinavit community (archive-listed) 18 samples, 17 ran (1 instrument-failed) · 1 unverified
Model in 227 papers big_vision/models/mlp_mixer.py ran Apache-2.0 (permissive) · 0a92f4de53a489b4 · report fixture: signature num_classes:int/0/int, variant:str/0/str · returned MlpMixer · level recorded 2026-09-24
dot_product_attention in 15 papers big_vision/models/attn_override.py ran Apache-2.0 (permissive) · 2c4ed3f75ab6ee14 · report fixture: signature query:ArrayImpl/4/float, key:ArrayImpl/4/float, value:ArrayImpl/4/float, bias:ArrayImpl/4/float, mask:ArrayImpl/4/bool, broadcast_dropout:bool/0/bool, dropout_rng:ArrayImpl/1/int, dropout_rate:float/0/float, deterministic:bool/0/bool, dtype:callable/0/?, precision:NoneType/0/? · returned tuple · level recorded 2026-09-24
dot_product_attention_weights big_vision/models/attn_override.py ran Apache-2.0 (permissive) · c8927d5d53a840b6 · report fixture: signature query:ArrayImpl/4/float, key:ArrayImpl/4/float, bias:ArrayImpl/4/float, mask:ArrayImpl/4/bool, broadcast_dropout:bool/0/bool, dropout_rng:ArrayImpl/1/int, dropout_rate:float/0/float, deterministic:bool/0/bool, dtype:callable/0/?, precision:NoneType/0/? · returned ArrayImpl · level recorded 2026-09-24
fix_old_checkpoints big_vision/models/bit.py ran Apache-2.0 (permissive) · 75f9a36fc8351778 · report fixture: signature params:FrozenDict/0/? · returned dict · level recorded 2026-09-24
get in 42 papers big_vision/datasets/core.py ran Apache-2.0 (permissive) · f40ba1fc76a56621 · report fixture: signature name:str/0/str, split:str/0/str, batch_size:int/0/int · returned MockDataSource · level recorded 2026-09-24
get_block_desc big_vision/models/bit.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 4f697aeaa3747cc2 · report fixture: signature depth:int/0/int · returned list · level recorded, date not recorded
get_count in 9 papers big_vision/optax.py ran Apache-2.0 (permissive) · 5c44a598f86dadfc · report fixture: signature opt_state:tuple/1/ScaleByScheduleState, jittable:bool/0/bool · returned int · level recorded 2026-09-24
get_posemb in 5 papers big_vision/models/vit.py ran Apache-2.0 (permissive) · ec1bf067066bb434 · report fixture: signature self:MockModule/0/?, typ:str/0/str, seqshape:tuple/1/int, width:int/0/int, name:str/0/str, dtype:callable/0/?, scales:list/1/int · returned ArrayImpl · level recorded 2026-09-24
magnitude in 5 papers big_vision/models/attn_override.py ran Apache-2.0 (permissive) · 9d78a212d314b83e · report fixture: signature x:ArrayImpl/4/float · returned ArrayImpl · level recorded 2026-09-24
make_for_inference big_vision/input_pipeline.py ran Apache-2.0 (permissive) · a0fec96972fe8326 · report fixture: signature data:_FlatMapDataset/0/?, preprocess_fn:callable/0/?, batch_size:int/0/int, num_ex_per_process:list/1/int, cache_raw:bool/0/bool, cache_final:bool/0/bool, num_parallel_calls:int/0/int, prefetch:int/0/int · returned tuple · level recorded 2026-09-24
npload big_vision/utils.py ran Apache-2.0 (permissive) · 2b3549774154825a · report fixture: signature fname:str/0/str · returned ndarray · level recorded 2026-09-24
onehot in 39 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
big_vision/utils.py ran Apache-2.0 (permissive) · 7b17682564107576 · report fixture: signature labels:ArrayImpl/1/int, num_classes:int/0/int, on_value:float/0/float, off_value:float/0/float · returned ArrayImpl · level recorded 2026-09-24
pad_shard_unpad big_vision/utils.py ran Apache-2.0 (permissive) · 5ad1f39431340fbb · report fixture: signature wrapped:callable/0/?, static_argnums:tuple/1/int, static_argnames:tuple/1/empty · returned function · level recorded 2026-09-24
posemb_conv big_vision/models/vit.py ran Apache-2.0 (permissive) · 4f5dd3aec9da6ede · report fixture: signature input_size:int/0/int, patch_size:int/0/int, width:int/0/int, scales:list/1/int, temperature:float/0/float, dtype:callable/0/? · returned ArrayImpl · level recorded 2026-09-24
posemb_sincos_2d in 20 papers big_vision/models/vit.py ran · honoured contract Apache-2.0 (permissive) · 2d67a8a756fe7cf8 · report fixture: signature h:int/0/int, w:int/0/int, width:int/0/int, temperature:float/0/float, dtype:callable/0/? · returned ArrayImpl · level recorded 2026-09-22
standardize in 47 papers big_vision/models/bit_paper.py ran Apache-2.0 (permissive) · c272f024d815d59d · report fixture: signature x:ArrayImpl/2/float, axis:int/0/int, eps:float/0/float · returned ArrayImpl · level recorded 2026-09-24
weight_standardize big_vision/models/bit.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 37b141b05f87de19 · report fixture: signature w:ArrayImpl/2/float, axis:int/0/int, eps:float/0/float · returned ArrayImpl · level recorded, date not recorded
find_states big_vision/optax.py unverified Apache-2.0 (permissive) · 1f64c95d3b75c46b · report
Repository not located 2 samples, 2 ran (0 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
pair in 101 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 6ba8cee9f5daea41 · report fixture: signature t:int/0/int · returned tuple · level recorded, date not recorded
posemb_sincos_2d in 20 papers repository not located ran · honoured contract licence of this copy not recorded · cfe18b9cc8afbfe9 · report fixture: signature h:int/0/int, w:int/0/int, dim:int/0/int, temperature:int/0/int, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22

Tasks

Data AugmentationImage Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual 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