Papers › Global Context Vision Transformers

Global Context Vision Transformers

20 Jun 2022arXiv:2206.09959archive 2025-07-28

Ali Hatamizadeh, Hongxu Yin, Greg Heinrich, Jan Kautz, Pavlo Molchanov

We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local self-attention, to effectively and efficiently model both long and short-range spatial interactions, without the need for expensive operations such as computing attention masks or shifting local windows. In addition, we address the lack of the inductive bias in ViTs, and propose to leverage a modified fused inverted residual blocks in our architecture. Our proposed GC ViT achieves state-of-the-art results across image classification, object detection and semantic segmentation tasks. On ImageNet-1K dataset for classification, the variants of GC ViT with 51M, 90M and 201M parameters achieve 84.3%, 85.0% and 85.7% Top-1 accuracy, respectively, at 224 image resolution and without any pre-training, hence surpassing comparably-sized prior art such as CNN-based ConvNeXt and ViT-based MaxViT and Swin Transformer by a large margin. Pre-trained GC ViT backbones in downstream tasks of object detection, instance segmentation, and semantic segmentation using MS COCO and ADE20K datasets outperform prior work consistently. Specifically, GC ViT with a 4-scale DINO detection head achieves a box AP of 58.3 on MS COCO dataset.

PaperPDFCodeCode Syntology ranMethod as code

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

Syntology 36 code samples harvested from 4 repositories linked to this paper: 21 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 12 ran (8 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 21 samples from 3 repositories, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nvlabs/gcvit officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 15 samples, 12 ran (4 instrument-failed) · 3 unverified report
rwightman/pytorch-image-models mentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
EMalagoli92/GCViT-TensorFlow mentioned on GitHubtfMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
awsaf49/gcvit-tf mentioned on GitHubtfSyntology: 16 samples, 5 ran (0 instrument-failed) · 11 unverified report
MindSpore-paper-code-3/code6 mindsporeSyntology: not harvested report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmclassification pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
shkarupa-alex/tfgcvit tfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

36 samples harvested: 21 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 15 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.

3ran · our draft was wrong
1ran; the contract check could not run
17ran
15unverified

Licence: 15 of the 36 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 4 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. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

nvlabs/gcvit official repository 15 samples, 12 ran (4 instrument-failed) · 3 unverified
FeatExtract models/gc_vit.py ran licence not identified · pointer only · e80b67aa418a782c · report fixture: returned FeatExtract · level recorded 2026-09-22
GlobalQueryGen models/gc_vit.py ran licence not identified · pointer only · 61c6465aba600b84 · report fixture: returned GlobalQueryGen · level recorded 2026-09-22
Mlp in 102 papers models/gc_vit.py ran licence not identified · pointer only · 54d976068690d3d1 · report fixture: returned Mlp · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
models/gc_vit.py ran fingerprinted licence not identified · pointer only · 40aaf4d47f39ab0b · report fixture: returned PatchEmbed · level recorded 2026-09-22
ReduceSize models/gc_vit.py ran licence not identified · pointer only · 82b08c759c9f6ca2 · report fixture: returned ReduceSize · level recorded 2026-09-22
SE in 13 papers models/gc_vit.py ran licence not identified · pointer only · c55dd199a66973af · report fixture: returned SE · level recorded 2026-09-22
WindowAttention in 50 papers models/gc_vit.py ran licence not identified · pointer only · 16c6d129c800a720 · report fixture: returned WindowAttention · level recorded 2026-09-22
WindowAttentionGlobal models/gc_vit.py ran licence not identified · pointer only · f7e8a124e89dc651 · report fixture: returned WindowAttentionGlobal · level recorded 2026-09-22
_to_channel_first models/gc_vit.py ran · our draft was wrong fingerprinted licence not identified · pointer only · def50b2e4eca5b7f · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_to_channel_last models/gc_vit.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 7b49c8af2301430b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/gc_vit.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 2cba2e8141170129 · report fixture: signature x:Tensor/4/float, window_size:int/0/int, h_w:int/0/int, w_w:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers models/gc_vit.py ran · our draft was wrong licence not identified · pointer only · 5adfa560a867040f · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int, h_w:int/0/int, w_w:int/0/int, B:int/0/int · returned Tensor · level recorded 2026-09-22
GCViT models/gc_vit.py unverified licence not identified · pointer only · 163b5911f9297e6c · report
GCViTBlock models/gc_vit.py unverified licence not identified · pointer only · 1ceb32009fe38260 · report
GCViTLayer models/gc_vit.py unverified licence not identified · pointer only · 422f8d129a49011f · report
EMalagoli92/GCViT-TensorFlow community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
norm_cdf in 8 papers gcvit_tensorflow/models/layers/utils.py ran fingerprinted MIT (permissive) · 1e7a21b70e475e05 · report fixture: signature x:float/0/float · returned float · level recorded 2026-09-25
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input
gcvit_tensorflow/models/layers/utils.py ran MIT (permissive) · 6fc63671bfbb6c99 · report fixture: signature shape:tuple/1/int, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float, dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-25
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
gcvit_tensorflow/models/utils.py ran fingerprinted MIT (permissive) · 4ea5c96c7699574c · report fixture: signature x:EagerTensor/4/float, window_size:int/0/int · returned EagerTensor · level recorded 2026-09-25
window_reverse in 296 papers gcvit_tensorflow/models/utils.py unverified MIT (permissive) · e19f5e7afc48b87a · report
awsaf49/gcvit-tf community (archive-listed) 16 samples, 5 ran (0 instrument-failed) · 11 unverified
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
gcvit/models/gcvit.py ran MIT (permissive) · cb662ef431014eb8 · report fixture: signature x:EagerTensor/3/float, training:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
FitWindow gcvit/models/gcvit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · a04bd08a4102e137 · report fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
gcvit/models/gcvit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · fc4f231a89851495 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
Mlp in 102 papers gcvit/models/gcvit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 175f4b05a6f94cf8 · report fixture: signature inputs:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
Resizing gcvit/models/gcvit.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · d4f0051dfe74829d · report fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
AdaptiveAveragePooling2D gcvit/models/gcvit.py unverified MIT (permissive) · f8e4623ae8d47882 · report
AdaptivePooling2D gcvit/models/gcvit.py unverified MIT (permissive) · 00abe3365641adfb · report
FeatExtract gcvit/models/gcvit.py unverified MIT (permissive) · a28f69fd86465824 · report
GCViT gcvit/models/gcvit.py unverified MIT (permissive) · 1c54430c64d45728 · report
GCViTBlock gcvit/models/gcvit.py unverified MIT (permissive) · cb77b8f164a09e19 · report
GCViTLevel gcvit/models/gcvit.py unverified MIT (permissive) · c45f3ff6bb9a8b4a · report
GlobalQueryGen gcvit/models/gcvit.py unverified MIT (permissive) · 72459b5e74464349 · report
ReduceSize gcvit/models/gcvit.py unverified MIT (permissive) · bacca661d0adddd1 · report
SE in 13 papers gcvit/models/gcvit.py unverified MIT (permissive) · bed567301fe24fc8 · report
Stem in 5 papers gcvit/models/gcvit.py unverified MIT (permissive) · 9c9a02a583a26d70 · report
WindowAttention in 50 papers gcvit/models/gcvit.py unverified MIT (permissive) · 1f2595f160725077 · report
shkarupa-alex/tfgcvit community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
preprocess_input in 26 papers tfgcvit/prep.py ran MIT (permissive) · 9cac895861c9b777 · report fixture: signature inputs:EagerTensor/4/float, dtype:NoneType/0/? · returned EagerTensor · level recorded 2026-09-25

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Global Context Vision Transformer (GC ViT) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Global Context Vision Transformer (GC ViT) (graph method: Global Context Vision Transformer (GC ViT)). 15 bricks; individually on a fixture: 12 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GCViT entry · level 0 · unverified · 163b5911f9297e6c
  2. GCViTLayer helper · level 0 · unverified · 422f8d129a49011f
  3. PatchEmbed helper · level 1 · ran · 40aaf4d47f39ab0b
  4. _to_channel_first helper · level 1 · ran · our draft was wrong · def50b2e4eca5b7f
  5. GCViTBlock helper · level 0 · unverified · 1ceb32009fe38260
  6. GlobalQueryGen helper · level 1 · ran · 61c6465aba600b84
  7. ReduceSize helper · level 1 · ran · 82b08c759c9f6ca2
  8. WindowAttention helper · level 1 · ran · 16c6d129c800a720
  9. WindowAttentionGlobal helper · level 1 · ran · f7e8a124e89dc651
  10. _to_channel_last helper · level 1 · ran · our draft was wrong · 7b49c8af2301430b
  11. Mlp helper · level 1 · ran · 54d976068690d3d1
  12. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · 2cba2e8141170129
  13. window_reverse helper · level 1 · ran · our draft was wrong · 5adfa560a867040f
  14. FeatExtract helper · level 1 · ran · e80b67aa418a782c
  15. SE helper · level 1 · ran · c55dd199a66973af

harvested Assembly for Global Context Vision Transformer (GC ViT) (graph method: Global Context Vision Transformer (GC ViT)). 16 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GCViT entry · level 0 · unverified · 1c54430c64d45728
  2. GCViTLevel helper · level 0 · unverified · c45f3ff6bb9a8b4a
  3. Identity helper · level 1 · ran · fc4f231a89851495
  4. Stem helper · level 0 · unverified · 9c9a02a583a26d70
  5. FitWindow helper · level 1 · ran · a04bd08a4102e137
  6. GCViTBlock model · level 0 · unverified · cb77b8f164a09e19
  7. GlobalQueryGen model · level 0 · unverified · 72459b5e74464349
  8. ReduceSize model · level 0 · unverified · bacca661d0adddd1
  9. Resizing helper · level 1 · ran · d4f0051dfe74829d
  10. DropPath helper · level 1 · ran · cb662ef431014eb8
  11. Mlp model · level 1 · ran · 175f4b05a6f94cf8
  12. WindowAttention model · level 0 · unverified · 1f2595f160725077
  13. FeatExtract model · level 0 · unverified · a28f69fd86465824
  14. SE helper · level 0 · unverified · bed567301fe24fc8
  15. AdaptiveAveragePooling2D helper · level 0 · unverified · f8e4623ae8d47882
  16. AdaptivePooling2D helper · level 0 · unverified · 00abe3365641adfb

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2206.09959") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationInductive BiasInstance SegmentationObject DetectionSegmentationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet GC ViT-B GFLOPs 14.8 #312 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-B Number of params 90M #312 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-B Top 1 Accuracy 84.5% #312 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-S GFLOPs 8.5 #368 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-S Number of params 51M #368 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-S Top 1 Accuracy 84.0% #368 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-T GFLOPs 4.7 #430 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-T Number of params 28M #430 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-T Top 1 Accuracy 83.4% #430 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-XT GFLOPs 2.6 #582 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-XT Number of params 20M #582 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-XT Top 1 Accuracy 82.0% #582 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-XXT GFLOPs 2.1 #740 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-XXT Number of params 12M #740 of 1060 Archive leaderboard report
Image Classification ImageNet GC ViT-XXT Top 1 Accuracy 79.8% #740 of 1060 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-B GFLOPs (512 x 512) 1348 #140 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-B Params (M) 125 #140 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-B Validation mIoU 49 #140 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-S GFLOPs (512 x 512) 1163 #149 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-S Params (M) 84 #149 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-S Validation mIoU 48.3 #149 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-T GFLOPs (512 x 512) 947 #175 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-T Params (M) 58 #175 of 235 Archive leaderboard report
Semantic Segmentation ADE20K GC ViT-T Validation mIoU 46.5 #175 of 235 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

Absolute Position EncodingsAdamAttentionBASEBPEConvNeXtDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformerVision 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