Papers › Visual Attention Network

Visual Attention Network

20 Feb 2022arXiv:2202.09741archive 2025-07-28

Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu

While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision. (1) Treating images as 1D sequences neglects their 2D structures. (2) The quadratic complexity is too expensive for high-resolution images. (3) It only captures spatial adaptability but ignores channel adaptability. In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings. Furthermore, we present a neural network based on LKA, namely Visual Attention Network (VAN). While extremely simple, VAN surpasses similar size vision transformers(ViTs) and convolutional neural networks(CNNs) in various tasks, including image classification, object detection, semantic segmentation, panoptic segmentation, pose estimation, etc. For example, VAN-B6 achieves 87.8% accuracy on ImageNet benchmark and set new state-of-the-art performance (58.2 PQ) for panoptic segmentation. Besides, VAN-B2 surpasses Swin-T 4% mIoU (50.1 vs. 46.1) for semantic segmentation on ADE20K benchmark, 2.6% AP (48.8 vs. 46.2) for object detection on COCO dataset. It provides a novel method and a simple yet strong baseline for the community. Code is available at https://github.com/Visual-Attention-Network.

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

Syntology 6 code samples harvested from 3 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 5 samples from 2 repositories, 5 ran (5 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 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

21 repositories listed; official and paper-mentioned ones first.

Visual-Attention-Network/VAN-Classification officialmentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
open-mmlab/mmclassification mentioned in paperpytorchApache-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
DarshanDeshpande/jax-models mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Networks with Stochastic Depth (arXiv:1603.09382; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (arXiv:2102.12122; that paper's own run record: 22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified), Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified) and 5 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
EMalagoli92/VAN-Classification-TensorFlow mentioned on GitHubtfMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Jittor-Image-Models/Jittor-Image-Models mentioned on GitHubpytorchSyntology: not harvested report
Visual-Attention-Network/VAN-Segmentation mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Westlake-AI/openmixup mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
chengtan9907/simvpv2 mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning (arXiv:2306.11249; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
facebookresearch/xformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Longformer: The Long-Document Transformer (arXiv:2004.05150; that paper's own run record: 22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified) and Self-attention Does Not Need O(n²) Memory (arXiv:2112.05682; that paper's own run record: 33 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 6 violated, 12 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
lucasjinreal/yolov7_d2 mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
sithu31296/semantic-segmentation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers (arXiv:2105.15203; that paper's own run record: 66 ran (of which 22 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 14 where Syntology's instrument failed) · 20 unverified), FaPN: Feature-aligned Pyramid Network for Dense Image Prediction (arXiv:2108.07058; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified) and A ConvNet for the 2020s (arXiv:2201.03545; that paper's own run record: 57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 2 honoured, 0 violated, 47 with no contract checked; 8 where Syntology's instrument failed) · 23 unverified); nothing checks that they implement this paper's method. report
Asthestarsfalll/VAN-MegEngine pytorchSyntology: not harvested report
MenghaoGuo/Awesome-Vision-Attentions Syntology: not harvested report
MindCode-4/code-1 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
Visual-Attention-Network/VAN-Jittor pytorchSyntology: not harvested report
flytocc/PaddleClas paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MixFormer: Mixing Features across Windows and Dimensions (arXiv:2204.02557; that paper's own run record: 10 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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
shkarupa-alex/tfvan tfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified 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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 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.

6ran

Licence: 0 of the 6 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. “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.

Visual-Attention-Network/VAN-Classification official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
load_model_weights in 6 papers models/van.py ran Apache-2.0 (permissive) · 07d3401919c8d206 · report fixture: signature model:callable/0/?, arch:str/0/str, kwargs:dict/0/? · returned MinimalVAN · level recorded 2026-09-24
EMalagoli92/VAN-Classification-TensorFlow community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
norm_cdf in 8 papers van_classification_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
van_classification_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
shkarupa-alex/tfvan community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
convert_name convert_weights.py ran fingerprinted MIT (permissive) · 365afdb1239780d8 · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-24
convert_weight convert_weights.py ran MIT (permissive) · 250a0be2cff73866 · report fixture: signature weight:Tensor/1/float, name:str/0/str · returned Tensor · level recorded 2026-09-24
preprocess_input in 26 papers tfvan/prep.py ran MIT (permissive) · 5e6f2f4822f14d6f · report fixture: signature inputs:EagerTensor/4/int · returned EagerTensor · level recorded 2026-09-24

Tasks

Image ClassificationInstance SegmentationObject DetectionPanoptic SegmentationPose EstimationSegmentationSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet VAN-B6 (22K, 384res) GFLOPs 114.3 #70 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B6 (22K, 384res) Number of params 200M #70 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B6 (22K, 384res) Top 1 Accuracy 87.8% #70 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B5 (22K, 384res) GFLOPs 50.6 #111 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B5 (22K, 384res) Top 1 Accuracy 87% #111 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B6 (22K) GFLOPs 38.9 #120 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B6 (22K) Number of params 200M #120 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B6 (22K) Top 1 Accuracy 86.9% #120 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B4 (22K, 384res) GFLOPs 35.9 #133 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B4 (22K, 384res) Number of params 60M #133 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B4 (22K, 384res) Top 1 Accuracy 86.6% #133 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B5 (22K) GFLOPs 17.2 #159 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B5 (22K) Number of params 90M #159 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B5 (22K) Top 1 Accuracy 86.3% #159 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B4 (22K) GFLOPs 12.2 #204 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B4 (22K) Top 1 Accuracy 85.7% #204 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B2 GFLOPs 5 #497 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B2 Number of params 26.6M #497 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B2 Top 1 Accuracy 82.8% #497 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B1 GFLOPs 2.5 #664 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B1 Number of params 13.9M #664 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B1 Top 1 Accuracy 81.1% #664 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B0 GFLOPs 0.9 #949 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B0 Number of params 4.1M #949 of 1060 Archive leaderboard report
Image Classification ImageNet VAN-B0 Top 1 Accuracy 75.4% #949 of 1060 Archive leaderboard report
Panoptic Segmentation COCO minival Visual Attention Network (VAN-B6 + Mask2Former) PQ 58.2 #10 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Visual Attention Network (VAN-B6 + Mask2Former) PQst 48.2 #10 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Visual Attention Network (VAN-B6 + Mask2Former) PQth 64.8 #10 of 31 Archive leaderboard report
Panoptic Segmentation COCO panoptic VAN-B6* PQ 58.2 #1 of 2 Archive leaderboard report
Semantic Segmentation ADE20K VAN-B6 Validation mIoU 54.7 #58 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Large (HamNet) Params (M) 55 #117 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Large (HamNet) Validation mIoU 50.2 #117 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Large Params (M) 49 #151 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Large Validation mIoU 48.1 #151 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Base (Semantic-FPN) Validation mIoU 46.7 #173 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Small Params (M) 18 #213 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Small Validation mIoU 42.9 #213 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Tiny Params (M) 8 #221 of 235 Archive leaderboard report
Semantic Segmentation ADE20K VAN-Tiny Validation mIoU 38.5 #221 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.

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