Papers › VOLO: Vision Outlooker for Visual Recognition

VOLO: Vision Outlooker for Visual Recognition

24 Jun 2021arXiv:2106.13112archive 2025-07-28

Li Yuan, Qibin Hou, Zihang Jiang, Jiashi Feng, Shuicheng Yan

Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their performance is still inferior to that of the latest SOTA CNNs if no extra data are provided. In this work, we try to close the performance gap and demonstrate that attention-based models are indeed able to outperform CNNs. We find a major factor limiting the performance of ViTs for ImageNet classification is their low efficacy in encoding fine-level features into the token representations. To resolve this, we introduce a novel outlook attention and present a simple and general architecture, termed Vision Outlooker (VOLO). Unlike self-attention that focuses on global dependency modeling at a coarse level, the outlook attention efficiently encodes finer-level features and contexts into tokens, which is shown to be critically beneficial to recognition performance but largely ignored by the self-attention. Experiments show that our VOLO achieves 87.1% top-1 accuracy on ImageNet-1K classification, which is the first model exceeding 87% accuracy on this competitive benchmark, without using any extra training data In addition, the pre-trained VOLO transfers well to downstream tasks, such as semantic segmentation. We achieve 84.3% mIoU score on the cityscapes validation set and 54.3% on the ADE20K validation set. Code is available at https://github.com/sail-sg/volo.

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 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 5 ran (4 with no instrument failure; 1 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

rwightman/pytorch-image-models officialmentioned 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
sail-sg/volo officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 5 ran (1 instrument-failed) · 1 unverified report
BR-IDL/PaddleViT paddleSyntology: 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
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: not harvested report
xmu-xiaoma666/External-Attention-pytorch pytorchSyntology: 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), RepVGG: Making VGG-style ConvNets Great Again (arXiv:2101.03697; that paper's own run record: 13 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified), Involution: Inverting the Inherence of Convolution for Visual Recognition (arXiv:2103.06255; that paper's own run record: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 7 samples that ran constructed an object rather than computing a result) and 4 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran; the contract check could not run
4ran
1unverified

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 sail-sg/volo. “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.

sail-sg/volo official repository 6 samples, 5 ran (1 instrument-failed) · 1 unverified
get_block in 40 papers models/volo.py ran Apache-2.0 (permissive) · 87a34d0211098d18 · report fixture: signature block_type:str/0/str, dim:int/0/int, num_heads:int/0/int, head_dim:int/0/int, mlp_ratio:float/0/float, qkv_bias:bool/0/bool, qk_scale:NoneType/0/?, drop:float/0/float, attn_drop:float/0/float, drop_path:float/0/float, act_layer:callable/0/?, norm_layer:callable/0/? · returned ClassBlock · level recorded 2026-09-25
outlooker_blocks models/volo.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · ba7779c554538760 · report fixture: signature block_fn:callable/0/?, index:int/0/int, dim:int/0/int, layers:list/1/int, num_heads:int/0/int, kernel_size:int/0/int, padding:int/0/int, stride:int/0/int, mlp_ratio:float/0/float, qkv_bias:bool/0/bool, qk_scale:NoneType/0/?, attn_drop:float/0/float, drop_path_rate:float/0/float · returned Sequential · level recorded 2026-09-24
resize_pos_embed in 102 papers utils/utils.py ran Apache-2.0 (permissive) · b3b01c5690550b6c · report fixture: signature posemb:Tensor/3/float, posemb_new:Tensor/3/float · returned Tensor · level recorded 2026-09-25
resize_pos_embed_4d utils/utils.py ran fingerprinted Apache-2.0 (permissive) · e0d164428f4b2b84 · report fixture: signature posemb:Tensor/4/float, posemb_new:Tensor/4/float · returned Tensor · level recorded 2026-09-25
resize_pos_embed_without_cls utils/utils.py ran fingerprinted Apache-2.0 (permissive) · 6aee19396cb78860 · report fixture: signature posemb:Tensor/3/float, posemb_new:Tensor/3/float · returned Tensor · level recorded 2026-09-25
rand_bbox in 63 papers models/volo.py unverified Apache-2.0 (permissive) · b66088e90761117d · report

Tasks

Domain GeneralizationImage ClassificationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization VizWiz-Classification VOLO-D5 Accuracy - All Images 57.2 #1 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification VOLO-D5 Accuracy - Clean Images 59.7 #1 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification VOLO-D5 Accuracy - Corrupted Images 51.8 #1 of 90 Archive leaderboard report
Image Classification ImageNet VOLO-D5 GFLOPs 412 #107 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D5 Number of params 296M #107 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D5 Top 1 Accuracy 87.1% #107 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D4 GFLOPs 197 #123 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D4 Number of params 193M #123 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D4 Top 1 Accuracy 86.8% #123 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D3 GFLOPs 67.9 #157 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D3 Number of params 86M #157 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D3 Top 1 Accuracy 86.3% #157 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D2 Number of params 59M #180 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D2 Top 1 Accuracy 86% #180 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D1 Number of params 27M #247 of 1060 Archive leaderboard report
Image Classification ImageNet VOLO-D1 Top 1 Accuracy 85.2% #247 of 1060 Archive leaderboard report
Image Classification ImageNet ReaL VOLO-D5 Accuracy 90.6% #15 of 57 Archive leaderboard report
Image Classification ImageNet ReaL VOLO-D4 Accuracy 90.5% #18 of 57 Archive leaderboard report
Image Classification ImageNet V2 VOLO-D5 Top 1 Accuracy 78 #14 of 33 Archive leaderboard report
Image Classification ImageNet V2 VOLO-D4 Top 1 Accuracy 77.8 #15 of 33 Archive leaderboard report
Image Classification VizWiz-Classification VOLO-D5 Accuracy 57.2 #1 of 1 Archive leaderboard report
Semantic Segmentation ADE20K VOLO-D5 Validation mIoU 54.3 #62 of 235 Archive leaderboard report
Semantic Segmentation Cityscapes val VOLO-D4 (MS, ImageNet1k pretrain) mIoU 84.3 #18 of 99 Archive leaderboard report
Semantic Segmentation Graz-02 VOLO-D5 Pixel Accuracy 85 #1 of 2 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