Papers › Vision GNN: An Image is Worth Graph of Nodes

Vision GNN: An Image is Worth Graph of Nodes

1 Jun 2022arXiv:2206.00272archive 2025-07-28

Kai Han, Yunhe Wang, Jianyuan Guo, Yehui Tang, Enhua Wu

Network architecture plays a key role in the deep learning-based computer vision system. The widely-used convolutional neural network and transformer treat the image as a grid or sequence structure, which is not flexible to capture irregular and complex objects. In this paper, we propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks. We first split the image to a number of patches which are viewed as nodes, and construct a graph by connecting the nearest neighbors. Based on the graph representation of images, we build our ViG model to transform and exchange information among all the nodes. ViG consists of two basic modules: Grapher module with graph convolution for aggregating and updating graph information, and FFN module with two linear layers for node feature transformation. Both isotropic and pyramid architectures of ViG are built with different model sizes. Extensive experiments on image recognition and object detection tasks demonstrate the superiority of our ViG architecture. We hope this pioneering study of GNN on general visual tasks will provide useful inspiration and experience for future research. The PyTorch code is available at https://github.com/huawei-noah/Efficient-AI-Backbones and the MindSpore code is available at https://gitee.com/mindspore/models.

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 34 code samples harvested from 5 repositories linked to this paper: 25 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 29 samples from 3 repositories, 23 ran (15 with no instrument failure; 8 where Syntology's instrument failed); community: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 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 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. 2 of the 25 samples that ran have no recorded date.

huawei-noah/CV-backbones officialmentioned in papermentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformer in Transformer (arXiv:2103.00112; that paper's own run record: 16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
huawei-noah/efficient-ai-backbones officialmentioned in papermentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
dvlab-research/rescom mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Parametric Contrastive Learning (arXiv:2107.12028; that paper's own run record: 1 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; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
gswycf/signgraph mentioned on GitHubpytorchSyntology: 19 samples, 14 ran (8 instrument-failed) · 5 unverified report
lccol/vig-eo mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
mirzaim/VisionGNN mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
2023-MindSpore-1/ms-code-217 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-7 mindsporeSyntology: not harvested report
robin-ex/ViG mindsporeSyntology: 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

34 samples harvested: 25 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 10 where Syntology's instrument failed) · 9 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
7ran; the contract check could not run
15ran
9unverified

Licence: 22 of the 34 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 5 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 1 sample 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.

huawei-noah/efficient-ai-backbones official repository 3 samples, 0 ran · 3 unverified
DeepGCN vig_pytorch/vig.py unverified no licence file found · pointer only · 28cfea9469d3520b · report
FFN in 37 papers vig_pytorch/vig.py unverified no licence file found · pointer only · 02f652b1a13d93ac · report
Stem in 5 papers vig_pytorch/vig.py unverified no licence file found · pointer only · 52ba09bd92b104eb · report
gswycf/signgraph community (archive-listed) 19 samples, 14 ran (8 instrument-failed) · 5 unverified
DenseDilated modules/gcn_lib/torch_vertex.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 119c797c7f57d6d4 · report fixture: returned DenseDilated · level recorded 2026-09-22
DenseDilatedKnnGraph modules/gcn_lib/torch_vertex.py ran · metamorphic tier: deterministic no licence file found · pointer only · b65d27ba607bc693 · report fixture: returned DenseDilatedKnnGraph · level recorded 2026-09-22
EdgeConv2d modules/gcn_lib/torch_vertex.py ran · metamorphic tier: deterministic no licence file found · pointer only · 246cabde6412ef6b · report fixture: returned EdgeConv2d · level recorded 2026-09-22
GraphConv2d modules/gcn_lib/torch_vertex.py ran · metamorphic tier: deterministic no licence file found · pointer only · b560c318f9098a55 · report fixture: returned GraphConv2d · level recorded 2026-09-22
GraphSAGE modules/gcn_lib/torch_vertex.py ran · metamorphic tier: deterministic no licence file found · pointer only · dd631a63dafc592e · report fixture: returned GraphSAGE · level recorded 2026-09-22
MRConv2d modules/gcn_lib/torch_vertex.py ran · metamorphic tier: deterministic no licence file found · pointer only · a2aa2f7e285a4594 · report fixture: returned MRConv2d · level recorded 2026-09-22
act_layer in 20 papers modules/gcn_lib/torch_vertex.py ran · our draft was wrong no licence file found · pointer only · 9cb7add8f210b472 · report fixture: signature act:str/0/str, inplace:bool/0/bool, neg_slope:float/0/float, n_prelu:int/0/int · returned ReLU · level recorded 2026-09-22
batched_index_select in 44 papers modules/gcn_lib/torch_vertex.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 996eec2334fe011e · report fixture: signature x:Tensor/4/float, idx:Tensor/3/int · returned Tensor · level recorded 2026-09-22
dense_knn_matrix modules/gcn_lib/torch_vertex.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 524d82561975519a · report fixture: signature x:Tensor/4/float, k:int/0/int, relative_pos:Tensor/3/float · returned Tensor · level recorded 2026-09-22
norm_layer in 17 papers modules/gcn_lib/torch_vertex.py ran · our draft was wrong no licence file found · pointer only · 09e6ddb17c0adf28 · report fixture: signature norm:str/0/str, nc:int/0/int · returned BatchNorm2d · level recorded 2026-09-22
pairwise_distance in 55 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 3, kind float, dtype float32
modules/gcn_lib/torch_vertex.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 82aeae314890e7ed · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
part_pairwise_distance modules/gcn_lib/torch_vertex.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 102d0e5b09e9b385 · report fixture: signature x:Tensor/3/float, start_idx:int/0/int, end_idx:int/0/int · returned Tensor · level recorded 2026-09-22
xy_dense_knn_matrix modules/gcn_lib/torch_vertex.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7fe31bf86f9187b8 · report fixture: signature x:Tensor/4/float, y:Tensor/4/float, k:int/0/int, relative_pos:Tensor/3/float · returned Tensor · level recorded 2026-09-22
xy_pairwise_distance modules/gcn_lib/torch_vertex.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 160401504e7d0dbb · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-22
BasicConv in 14 papers modules/gcn_lib/torch_vertex.py unverified no licence file found · pointer only · e95e0284f030b79b · report
DyGraphConv2d modules/gcn_lib/torch_vertex.py unverified no licence file found · pointer only · 85beb50061cdf64c · report
GINConv2d modules/gcn_lib/torch_vertex.py unverified no licence file found · pointer only · a0b00f43341b5121 · report
Grapher modules/gcn_lib/torch_vertex.py unverified no licence file found · pointer only · 5ab123da9ff9a2d5 · report
get_2d_relative_pos_embed in 5 papers modules/gcn_lib/torch_vertex.py unverified no licence file found · pointer only · 5ae9597352254138 · report
lccol/vig-eo community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
compute_edge_index models/utils.py ran Apache-2.0 (permissive) · a5df825822ba8636 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float, k:int/0/int, distance:str/0/str, is_batched:bool/0/bool · returned Tensor · level recorded 2026-09-24
compute_split_sizes run_training.py ran Apache-2.0 (permissive) · ee2406844fe2831e · report fixture: signature split:str/0/str, size:int/0/int · returned tuple · level recorded 2026-09-24
convert_neigh_list_to_edge_index models/utils.py ran Apache-2.0 (permissive) · 72e6fd8e9496b74f · report fixture: signature nn_idx:Tensor/3/int, y_max:NoneType/0/?, is_batched:bool/0/bool · returned Tensor · level recorded 2026-09-24
get_activation_layer in 9 papers models/utils.py ran Apache-2.0 (permissive) · 32a549c7e940abbb · report fixture: signature act:str/0/str · returned ReLU · level recorded 2026-09-24
normalize_image in 28 papers run_training.py ran Apache-2.0 (permissive) · 6f6471b9561767b8 · report fixture: signature data:dict/0/?, mean:Tensor/1/float, std:Tensor/1/float · returned dict · level recorded 2026-09-24
parse_train_string run_training.py ran fingerprinted Apache-2.0 (permissive) · 680818c85f065e07 · report fixture: signature entry:str/0/str · returned list · level recorded 2026-09-24
mirzaim/VisionGNN community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
SimplePatchifier model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 9dea5f82e4174cc6 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
TwoLayerNN model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 83ee8781c7b699e2 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ViGBlock model.py ran Apache-2.0 (permissive) · 0baa10d91e583fcc · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
VGNN model.py unverified Apache-2.0 (permissive) · 1b638d9a262ff4f6 · report
hustvl/ViG community 2 samples, 2 ran (2 instrument-failed) · 0 unverified
reshape_for_broadcast in 90 papers
census: 6 implementations from 10 papers, 1 distinct output on one shared input
classification/models/vig.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 20ff6d11dd593018 · report fixture: signature freqs_cis:Tensor/2/complex, x:Tensor/4/float · returned Tensor · level recorded, date not recorded
resize_pos_embed in 102 papers classification/models/vig.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 212a5d16eef34d1d · report fixture: signature pos_embed:Tensor/3/float, src_shape:tuple/1/int, dst_shape:tuple/1/int, mode:str/0/str, num_extra_tokens:int/0/int · returned Tensor · level recorded, date not recorded

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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Vision GNN (ViG) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Vision GNN (ViG) (graph method: Vision GNN (ViG)). 22 bricks; individually on a fixture: 14 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. Grapher entry · level 0 · unverified · 5ab123da9ff9a2d5
  2. DyGraphConv2d helper · level 0 · unverified · 85beb50061cdf64c
  3. get_2d_relative_pos_embed helper · level 0 · unverified · 5ae9597352254138
  4. DenseDilatedKnnGraph helper · level 1 · ran · b65d27ba607bc693
  5. GraphConv2d helper · level 1 · ran · b560c318f9098a55
  6. get_2d_sincos_pos_embed helper · level 0 · unverified · 43ab33710deb02f8
  7. DenseDilated helper · level 1 · ran · 119c797c7f57d6d4
  8. dense_knn_matrix helper · level 1 · ran; the contract check could not run (RAISES) · 524d82561975519a
  9. xy_dense_knn_matrix helper · level 1 · ran; the contract check could not run (RAISES) · 7fe31bf86f9187b8
  10. EdgeConv2d helper · level 1 · ran · 246cabde6412ef6b
  11. GINConv2d helper · level 0 · unverified · a0b00f43341b5121
  12. GraphSAGE helper · level 1 · ran · dd631a63dafc592e
  13. MRConv2d helper · level 1 · ran · a2aa2f7e285a4594
  14. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  15. pairwise_distance helper · level 1 · ran; the contract check could not run (RAISES) · 82aeae314890e7ed
  16. part_pairwise_distance helper · level 1 · ran · our draft was wrong · 102d0e5b09e9b385
  17. xy_pairwise_distance helper · level 1 · ran; the contract check could not run (RAISES) · 160401504e7d0dbb
  18. BasicConv helper · level 0 · unverified · e95e0284f030b79b
  19. batched_index_select helper · level 1 · ran; the contract check could not run (RAISES) · 996eec2334fe011e
  20. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c
  21. act_layer helper · level 1 · ran · our draft was wrong · 9cb7add8f210b472
  22. norm_layer helper · level 1 · ran · our draft was wrong · 09e6ddb17c0adf28

harvested Assembly for Vision GNN (ViG) (graph method: Vision GNN (ViG)). 3 bricks; individually on a fixture: 0 ran · 3 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. DeepGCN entry · level 0 · unverified · 28cfea9469d3520b
  2. FFN model · level 0 · unverified · 02f652b1a13d93ac
  3. Stem model · level 0 · unverified · 52ba09bd92b104eb

harvested Assembly for Vision GNN (ViG) (graph method: Vision GNN (ViG)). 4 bricks; individually on a fixture: 3 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; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. VGNN entry · level 0 · unverified · 1b638d9a262ff4f6
  2. SimplePatchifier model · level 1 · ran · 9dea5f82e4174cc6
  3. ViGBlock model · level 1 · ran · 0baa10d91e583fcc
  4. TwoLayerNN helper · level 1 · ran · 83ee8781c7b699e2

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="2206.00272") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet Pyramid ViG-B GFLOPs 16.8 #400 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-B Number of params 92.6M #400 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-B Top 1 Accuracy 83.7% #400 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-M GFLOPs 8.9 #470 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-M Number of params 51.7M #470 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-M Top 1 Accuracy 83.1% #470 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-S GFLOPs 4.6 #575 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-S Number of params 27.3M #575 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-S Top 1 Accuracy 82.1% #575 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-Ti GFLOPs 1.7 #846 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-Ti Number of params 10.7M #846 of 1060 Archive leaderboard report
Image Classification ImageNet Pyramid ViG-Ti Top 1 Accuracy 78.2% #846 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

Convolution

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