Papers › Lite-HRNet: A Lightweight High-Resolution Network

Lite-HRNet: A Lightweight High-Resolution Network

13 Apr 2021CVPR 2021 1arXiv:2104.06403archive 2025-07-28

Changqian Yu, Bin Xiao, Changxin Gao, Lu Yuan, Lei Zhang, Nong Sang, Jingdong Wang

We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular lightweight networks, such as MobileNet, ShuffleNet, and Small HRNet. We find that the heavily-used pointwise (1x1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks. The complexity of channel weighting is linear w.r.t the number of channels and lower than the quadratic time complexity for pointwise convolutions. Our solution learns the weights from all the channels and over multiple resolutions that are readily available in the parallel branches in HRNet. It uses the weights as the bridge to exchange information across channels and resolutions, compensating the role played by the pointwise (1x1) convolution. Lite-HRNet demonstrates superior results on human pose estimation over popular lightweight networks. Moreover, Lite-HRNet can be easily applied to semantic segmentation task in the same lightweight manner. The code and models have been publicly available at https://github.com/HRNet/Lite-HRNet.

PaperPDFConference PDFCodeCode 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

The archive's official repository (HRNet/Lite-HRNet) was not harvested; the 29 samples below come from 3 community repositories.

Syntology 29 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 29 samples from 3 repositories, 13 ran (11 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 4 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.

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

HRNet/Lite-HRNet officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
viet-hoang-99/Lite_HRnet_vh mentioned on GitHubpytorchSyntology: 13 samples, 3 ran (1 instrument-failed) · 10 unverified report
zh320/realtime-semantic-segmentation-pytorch mentioned on GitHubpytorchSyntology: 14 samples, 9 ran (1 instrument-failed) · 5 unverified report
zimka/lite_hrnet_tfk mentioned on GitHubtfSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
alibaba/EasyCV pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-End Object Detection with Transformers (arXiv:2005.12872; that paper's own run record: 70 ran (of which 45 constructed an object rather than computing a result; 62 with no instrument failure: 2 honoured, 1 violated, 59 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified), Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified), Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
code-implementation1/Code4 mindsporeSyntology: not harvested report
code-implementation1/Code4 mindsporeSyntology: not harvested report
kingcong/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Image Patch is a Wave: Phase-Aware Vision MLP (arXiv:2111.12294; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
open-edge-platform/training_extensions pytorchApache-2.0Syntology: not harvested report
open-mmlab/mmpose pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (arXiv:2312.07526; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
xiuyu0000/papers_with_examples mindsporeSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
yangyucheng000/LiteHRNet 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

29 samples harvested: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 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.

2ran · our draft was wrong
11ran
16unverified

Licence: 13 of the 29 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”. For 2 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.

viet-hoang-99/Lite_HRnet_vh community (archive-listed) 13 samples, 3 ran (1 instrument-failed) · 10 unverified
ConvModule in 8 papers lib/models/lite_hrnet.py ran fingerprinted no licence file found · pointer only · 7f5303fab6ab6aa5 · report fixture: returned ConvModule · level recorded 2026-09-22
GlobalAvgPool2d lib/models/lite_hrnet.py ran fingerprinted no licence file found · pointer only · 9778e2200dd35fd6 · report fixture: returned GlobalAvgPool2d · level recorded 2026-09-22
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input
lib/models/lite_hrnet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 01a5b048271d7607 · report fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-22
ConditionalChannelWeighting lib/models/lite_hrnet.py unverified no licence file found · pointer only · b12bbf8bdd283fd4 · report
CrossResolutionWeighting lib/models/lite_hrnet.py unverified no licence file found · pointer only · cf2130259d852422 · report
DepthwiseSeparableConvModule lib/models/lite_hrnet.py unverified no licence file found · pointer only · 7228e155ce724b07 · report
IterativeHead lib/models/lite_hrnet.py unverified no licence file found · pointer only · 998cb1c170207bce · report
LiteHRModule lib/models/lite_hrnet.py unverified no licence file found · pointer only · 619eac8f9d49f5ae · report
LiteHRNet lib/models/lite_hrnet.py unverified no licence file found · pointer only · a532cb9416bf3cef · report
ShuffleUnit lib/models/lite_hrnet.py unverified no licence file found · pointer only · d77006bb3a2e1085 · report
SpatialWeighting lib/models/lite_hrnet.py unverified no licence file found · pointer only · bcd14fbd45f266e7 · report
Stem in 5 papers lib/models/lite_hrnet.py unverified no licence file found · pointer only · 63a7e1662cd623f7 · report
constant_init in 10 papers lib/models/lite_hrnet.py unverified no licence file found · pointer only · a10a9642969fb96e · report
zh320/realtime-semantic-segmentation-pytorch community (archive-listed) 14 samples, 9 ran (1 instrument-failed) · 5 unverified
CrossResolutionWeightModule models/lite_hrnet.py ran Apache-2.0 (permissive) · 82e1655d4701b970 · report fixture: signature feats:list/1/Tensor · returned tuple · level recorded 2026-09-24
DSConvBNAct models/lite_hrnet.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 7c4e84db2f49cedf · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
DownsampleBlock models/lite_hrnet.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · ae084989a6c34e09 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
PWConvBNAct models/lite_hrnet.py ran fingerprinted Apache-2.0 (permissive) · c1585d202a6ecc57 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
RepresentationHead models/lite_hrnet.py ran Apache-2.0 (permissive) · 8f3ca13d6f37ea95 · report fixture: signature feats:list/1/Tensor · returned Tensor · level recorded 2026-09-24
ShuffleBlock models/lite_hrnet.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 4a4ad8085453946a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SpatialWeightModule models/lite_hrnet.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 50b9800a371ca617 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
UpsampleBlock in 9 papers models/lite_hrnet.py ran fingerprinted Apache-2.0 (permissive) · 21e87966c949f4a8 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input
models/lite_hrnet.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 64e0d826e27a411e · report fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-22
CCWBlock models/lite_hrnet.py unverified Apache-2.0 (permissive) · 8b8d270632be0efe · report
DWConvBNAct models/lite_hrnet.py unverified Apache-2.0 (permissive) · 1656ec64a6120ea4 · report
FusionBlock models/lite_hrnet.py unverified Apache-2.0 (permissive) · 29d5d4d24965174a · report
LiteHRNet models/lite_hrnet.py unverified Apache-2.0 (permissive) · 8caec653733b1dc1 · report
StageBlock models/lite_hrnet.py unverified Apache-2.0 (permissive) · 6770080877034782 · report
xiuyu0000/papers_with_examples community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_ax in 5 papers maskrcnn/src/infer.py ran Apache-2.0 (permissive) · 46bf80043a90eddf · report fixture: signature rows:int/0/int, cols:int/0/int, size:int/0/int · returned ndarray · level recorded 2026-09-24
random_colors in 12 papers maskrcnn/src/infer.py unverified Apache-2.0 (permissive) · 255e1c60a7eead8b · report

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 Lite-HRNet (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Lite-HRNet (graph method: Lite-HRNet). 14 bricks; individually on a fixture: 3 ran (of which 2 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) · 11 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. LiteHRNet entry · level 0 · unverified · a532cb9416bf3cef
  2. IterativeHead model · level 0 · unverified · 998cb1c170207bce
  3. LiteHRModule model · level 0 · unverified · 619eac8f9d49f5ae
  4. Stem model · level 0 · unverified · 63a7e1662cd623f7
  5. DepthwiseSeparableConvModule helper · level 0 · unverified · 7228e155ce724b07
  6. ConditionalChannelWeighting model · level 0 · unverified · b12bbf8bdd283fd4
  7. ShuffleUnit model · level 0 · unverified · d77006bb3a2e1085
  8. ConvModule helper · level 1 · ran · 7f5303fab6ab6aa5
  9. channel_shuffle helper · level 1 · ran · our draft was wrong · 01a5b048271d7607
  10. CrossResolutionWeighting model · level 0 · unverified · cf2130259d852422
  11. SpatialWeighting helper · level 0 · unverified · bcd14fbd45f266e7
  12. constant_init helper · level 0 · unverified · a10a9642969fb96e
  13. kaiming_init helper · level 0 · unverified · 94b6a7396eb44132
  14. GlobalAvgPool2d helper · level 1 · ran · 9778e2200dd35fd6

harvested Assembly for Lite-HRNet (graph method: Lite-HRNet). 18 bricks; individually on a fixture: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. LiteHRNet entry · level 0 · unverified · 8caec653733b1dc1
  2. ConvBNAct helper · level 1 · ran · baac3ba72d9b0da1
  3. DSConvBNAct helper · level 1 · ran · 7c4e84db2f49cedf
  4. RepresentationHead model · level 1 · ran · 8f3ca13d6f37ea95
  5. ShuffleBlock model · level 1 · ran · 4a4ad8085453946a
  6. StageBlock model · level 0 · unverified · 6770080877034782
  7. register_model helper · level 0 · unverified · 70f1b7f8523ba6a8
  8. Activation helper · level 1 · ran · f3dd5914b236afcb
  9. DWConvBNAct helper · level 0 · unverified · 1656ec64a6120ea4
  10. PWConvBNAct helper · level 1 · ran · c1585d202a6ecc57
  11. conv1x1 helper · level 1 · ran · our draft was wrong · 1cb17a8a8a22bc6c
  12. channel_shuffle helper · level 1 · ran · our draft was wrong · 64e0d826e27a411e
  13. CCWBlock model · level 0 · unverified · 8b8d270632be0efe
  14. CrossResolutionWeightModule model · level 1 · ran · 82e1655d4701b970
  15. FusionBlock model · level 0 · unverified · 29d5d4d24965174a
  16. SpatialWeightModule model · level 1 · ran · 50b9800a371ca617
  17. DownsampleBlock model · level 1 · ran · ae084989a6c34e09
  18. UpsampleBlock model · level 1 · ran · 21e87966c949f4a8

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="2104.06403") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Pose EstimationReal-Time Semantic SegmentationSemantic SegmentationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation COCO test-dev Lite-HRNet-30 AP 69.7 #34 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-30 AP50 90.7 #34 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-30 AP75 77.5 #34 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-30 APL 75.0 #34 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-30 APM 66.9 #34 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-30 AR 75.4 #34 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-18 AP 66.9 #37 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-18 AP50 89.4 #37 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-18 AP75 74.4 #37 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-18 APL 72.2 #37 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-18 APM 64.0 #37 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Lite-HRNet-18 AR 72.6 #37 of 47 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

1x1 ConvolutionAverage PoolingBatch NormalizationChannel ShuffleConvolutionDense ConnectionsDepthwise ConvolutionGlobal Average PoolingGrouped ConvolutionGroupwise Point ConvolutionHRNetMax PoolingPointwise ConvolutionReLUResidual ConnectionShuffleNetShuffleNet BlockSoftmax

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