Papers › Vision GNN: An Image is Worth Graph of Nodes
Vision GNN: An Image is Worth Graph of Nodes
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.
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):
get_harvested_code_for_paper(arxiv_id="2206.00272")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2206.00272", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2206.00272")
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:
- huawei-noah/CV-backbones, official repository: harvested for another paper, listed under the repository
- dvlab-research/rescom, community (archive-listed): harvested for another paper, listed under the repository
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.
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.
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.
28cfea9469d3520b · report
02f652b1a13d93ac · report
52ba09bd92b104eb · report
119c797c7f57d6d4 · report
fixture: returned DenseDilated · level recorded 2026-09-22 b65d27ba607bc693 · report
fixture: returned DenseDilatedKnnGraph · level recorded 2026-09-22 246cabde6412ef6b · report
fixture: returned EdgeConv2d · level recorded 2026-09-22 b560c318f9098a55 · report
fixture: returned GraphConv2d · level recorded 2026-09-22 dd631a63dafc592e · report
fixture: returned GraphSAGE · level recorded 2026-09-22 a2aa2f7e285a4594 · report
fixture: returned MRConv2d · level recorded 2026-09-22 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 996eec2334fe011e · report
fixture: signature x:Tensor/4/float, idx:Tensor/3/int · returned Tensor · level recorded 2026-09-22 524d82561975519a · report
fixture: signature x:Tensor/4/float, k:int/0/int, relative_pos:Tensor/3/float · returned Tensor · level recorded 2026-09-22 09e6ddb17c0adf28 · report
fixture: signature norm:str/0/str, nc:int/0/int · returned BatchNorm2d · level recorded 2026-09-22 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 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 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 160401504e7d0dbb · report
fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-22 e95e0284f030b79b · report
85beb50061cdf64c · report
a0b00f43341b5121 · report
5ab123da9ff9a2d5 · report
5ae9597352254138 · report
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 ee2406844fe2831e · report
fixture: signature split:str/0/str, size:int/0/int · returned tuple · level recorded 2026-09-24 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 32a549c7e940abbb · report
fixture: signature act:str/0/str · returned ReLU · level recorded 2026-09-24 6f6471b9561767b8 · report
fixture: signature data:dict/0/?, mean:Tensor/1/float, std:Tensor/1/float · returned dict · level recorded 2026-09-24 680818c85f065e07 · report
fixture: signature entry:str/0/str · returned list · level recorded 2026-09-24 9dea5f82e4174cc6 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 83ee8781c7b699e2 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 0baa10d91e583fcc · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24 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 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
- Grapher entry · level 0 · unverified ·
5ab123da9ff9a2d5 - DyGraphConv2d helper · level 0 · unverified ·
85beb50061cdf64c - get_2d_relative_pos_embed helper · level 0 · unverified ·
5ae9597352254138 - DenseDilatedKnnGraph helper · level 1 · ran ·
b65d27ba607bc693 - GraphConv2d helper · level 1 · ran ·
b560c318f9098a55 - get_2d_sincos_pos_embed helper · level 0 · unverified ·
43ab33710deb02f8 - DenseDilated helper · level 1 · ran ·
119c797c7f57d6d4 - dense_knn_matrix helper · level 1 · ran; the contract check could not run (RAISES) ·
524d82561975519a - xy_dense_knn_matrix helper · level 1 · ran; the contract check could not run (RAISES) ·
7fe31bf86f9187b8 - EdgeConv2d helper · level 1 · ran ·
246cabde6412ef6b - GINConv2d helper · level 0 · unverified ·
a0b00f43341b5121 - GraphSAGE helper · level 1 · ran ·
dd631a63dafc592e - MRConv2d helper · level 1 · ran ·
a2aa2f7e285a4594 - get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified ·
f10004e059714d42 - pairwise_distance helper · level 1 · ran; the contract check could not run (RAISES) ·
82aeae314890e7ed - part_pairwise_distance helper · level 1 · ran · our draft was wrong ·
102d0e5b09e9b385 - xy_pairwise_distance helper · level 1 · ran; the contract check could not run (RAISES) ·
160401504e7d0dbb - BasicConv helper · level 0 · unverified ·
e95e0284f030b79b - batched_index_select helper · level 1 · ran; the contract check could not run (RAISES) ·
996eec2334fe011e - get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified ·
12035a2f77d8016c - act_layer helper · level 1 · ran · our draft was wrong ·
9cb7add8f210b472 - 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
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
- VGNN entry · level 0 · unverified ·
1b638d9a262ff4f6 - SimplePatchifier model · level 1 · ran ·
9dea5f82e4174cc6 - ViGBlock model · level 1 · ran ·
0baa10d91e583fcc - 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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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