Papers › Deep High-Resolution Representation Learning for Visual Recognition

Deep High-Resolution Representation Learning for Visual Recognition

20 Aug 2019arXiv:1908.07919archive 2025-07-28

Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, Bin Xiao

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet.

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 34 code samples harvested from 7 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 34 samples from 7 repositories, 21 ran (16 with no instrument failure; 5 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 14 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 21 samples that ran has no recorded date.

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

open-mmlab/mmdetection mentioned in paperpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 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; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
HRNet/HRNet-Facial-Landmark-Detection mentioned on GitHubpytorchMITSyntology: 12 samples, 7 ran (2 instrument-failed) · 5 unverified report
HRNet/HRNet-Image-Classification mentioned on GitHubpytorchMITSyntology: 3 samples, 0 ran · 3 unverified report
HRNet/HRNet-MaskRCNN-Benchmark mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep High-Resolution Representation Learning for Human Pose Estimation (arXiv:1902.09212; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
HRNet/HRNet-Object-Detection mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
HRNet/HRNet-Semantic-Segmentation mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation (arXiv:1909.11065; that paper's own run record: 5 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; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
alililia/ascend_HRNetW48_cls mentioned on GitHubmindsporeApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
anshky/HR-NET mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
baoshengyu/deep-high-resolution-net.pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
eshaanagarwal/hr-net-implementation mentioned on GitHubtfSyntology: not harvested report
gox-ai/hrnet-pose-api mentioned on GitHubpytorchMITSyntology: not harvested report
kingcong/gpu_HRNetW48_cls mentioned on GitHubmindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
leoxiaobin/deep-high-resolution-net.pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks (arXiv:2105.06152; that paper's own run record: 14 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
mindspore-lab/mindone mentioned on GitHubmindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
mlpc-ucsd/PRTR mentioned on GitHubpytorchSyntology: 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) and Pose Recognition with Cascade Transformers (arXiv:2104.06976; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
pikabite/segmentations_tf2 mentioned on GitHubtfSyntology: not harvested report
sdll/hrnet-pose-estimation mentioned on GitHubpytorchMITSyntology: not harvested report
shuuchen/HRNet mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
sithu31296/pose-estimation mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Human Pose Regression with Residual Log-likelihood Estimation (arXiv:2107.11291; that paper's own run record: 10 ran (of which 2 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) · 1 unverified); nothing checks that they implement this paper's method. report
w-sugar/prtr mentioned on GitHubpytorchSyntology: 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) and Pose Recognition with Cascade Transformers (arXiv:2104.06976; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
yukichou/PET mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
2023-MindSpore-1/ms-code-162 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-214 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-214 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
CSAILVision/semantic-segmentation-pytorch pytorchBSD-3-ClauseSyntology: 8 samples, 7 ran (3 instrument-failed) · 1 unverified report
Calylyli/Mindsporehrnet mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
Mind23-2/MindCode-4 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: 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
PaddlePaddle/PaddleSeg paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow (arXiv:2109.09406; that paper's own run record: 5 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
megvii-research/basecls Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResMLP: Feedforward networks for image classification with data-efficient training (arXiv:2105.03404; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 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; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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
open-mmlab/mmsegmentation pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Perceptual Artifacts Localization for Image Synthesis Tasks (arXiv:2310.05590; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
shijianjian/HRNet_Keras tfSyntology: not harvested report
yangyucheng000/HRNetW48_cls mindsporeSyntology: not harvested report
yuanyuanli85/tf-hrnet tfBSD-3-ClauseSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified 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: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
2ran; the contract check could not run
15ran
13unverified

Licence: 21 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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.

HRNet/HRNet-Facial-Landmark-Detection community (archive-listed) 12 samples, 7 ran (2 instrument-failed) · 5 unverified
compute_nme lib/core/evaluation.py ran MIT recorded; this copy not marked cleared · pointer only · 6de0c395f2ed480f · report fixture: signature preds:Tensor/3/float, meta:dict/0/? · returned ndarray · level recorded 2026-09-24
conv3x3 in 1,376 papers lib/models/hrnet.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
create_logger in 172 papers lib/utils/utils.py ran MIT recorded; this copy not marked cleared · pointer only · d40435a99888f5a8 · report fixture: signature cfg:Config/0/?, cfg_name:str/0/str, phase:str/0/str · returned tuple · level recorded 2026-09-24
get_3rd_point in 8 papers lib/utils/transforms.py ran; the contract check could not run (RAISES) MIT recorded; this copy not marked cleared · pointer only · 9084d28f30c5495b · report fixture: signature a:ndarray/1/float, b:ndarray/1/float · returned ndarray · level recorded 2026-09-22
get_dir in 14 papers lib/utils/transforms.py ran · violated contract fingerprinted MIT recorded; this copy not marked cleared · pointer only · 5d546e1ecbee1866 · report fixture: signature src_point:list/1/float, rot_rad:float/0/float · returned list · level recorded 2026-09-22
get_optimizer in 228 papers lib/utils/utils.py ran MIT recorded; this copy not marked cleared · pointer only · f22f739c65e1ada2 · report fixture: signature cfg:Config/0/?, model:callable/0/? · returned SGD · level recorded 2026-09-24
get_preds in 18 papers lib/core/evaluation.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 8edd86bd9a43d59e · report fixture: signature scores:Tensor/4/float · returned Tensor · level recorded 2026-09-24
decode_preds lib/core/evaluation.py unverified MIT recorded; this copy not marked cleared · pointer only · e05de20d97ad0edc · report
fliplr_joints lib/utils/transforms.py unverified MIT recorded; this copy not marked cleared · pointer only · c2d2699886a4a219 · report
get_face_alignment_net lib/models/hrnet.py unverified MIT recorded; this copy not marked cleared · pointer only · 9011a68305d287a7 · report
inference in 65 papers lib/core/function.py unverified MIT recorded; this copy not marked cleared · pointer only · 294428702976ffdf · report
validate in 313 papers lib/core/function.py unverified MIT recorded; this copy not marked cleared · pointer only · 72f5b582b4e52e05 · report
HRNet/HRNet-Image-Classification community (archive-listed) 3 samples, 0 ran · 3 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
lib/core/evaluate.py unverified MIT recorded; this copy not marked cleared · pointer only · 390a8904d4707b9d · report
get_cls_net lib/models/cls_hrnet.py unverified MIT recorded; this copy not marked cleared · pointer only · 2536e03f883a249b · report
get_model_summary lib/utils/modelsummary.py unverified MIT recorded; this copy not marked cleared · pointer only · c6f52ade1e2640aa · report
alililia/ascend_HRNetW48_cls community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
calculate_fan_in_and_fan_out src/utils.py ran fingerprinted Apache-2.0 (permissive) · 74bebe7a4353815b · report fixture: signature shape:tuple/1/int · returned tuple · level recorded 2026-09-24
get_linear_lr src/utils.py ran Apache-2.0 (permissive) · da92159bb9c47108 · report fixture: signature base_lr:float/0/float, total_epoch:int/0/int, spe:int/0/int, lr_init:float/0/float, lr_end:float/0/float, warmup_epoch:int/0/int · returned list · level recorded 2026-09-24
anshky/HR-NET community (archive-listed) 1 sample, 0 ran · 1 unverified
get_pose_net in 15 papers lib/models/pose_hrnet.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 2534c81208f21998 · report
yukichou/PET community (archive-listed) 1 sample, 0 ran · 1 unverified
get_cls_net lib/models/cls_hrnet.py unverified MIT (permissive) · ab06e83afc0afd03 · report
CSAILVision/semantic-segmentation-pytorch community (archive-listed) 8 samples, 7 ran (3 instrument-failed) · 1 unverified
as_variable mit_semseg/lib/utils/th.py ran fingerprinted BSD-3-Clause (permissive) · 10bb6a2d70d61ca6 · report fixture: signature obj:Tensor/2/float · returned Tensor · level recorded 2026-09-25
find_recursive mit_semseg/utils.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) here; the stored copy is pointer only · 6890565633b480b8 · report fixture: signature root_dir:str/0/str, ext:str/0/str · returned list · level recorded 2026-09-25
imresize in 28 papers mit_semseg/dataset.py ran BSD-3-Clause (permissive) here; the stored copy is pointer only · e23968c493407287 · report fixture: signature im:Image/0/?, size:tuple/1/int, interp:str/0/str · returned Image · level recorded 2026-09-25
load_url in 9 papers mit_semseg/models/utils.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · d087e320591e6ba7 · report fixture: signature url:str/0/str, model_dir:str/0/str, map_location:str/0/str · returned dict · level recorded 2026-09-25
mark_volatile mit_semseg/lib/utils/th.py ran fingerprinted BSD-3-Clause (permissive) · 32f45cf75891bd16 · report fixture: signature obj:Tensor/2/float · returned Tensor · level recorded 2026-09-25
setup_logger in 122 papers mit_semseg/utils.py ran BSD-3-Clause (permissive) here; the stored copy is pointer only · b50608a902a34b99 · report fixture: signature distributed_rank:int/0/int, filename:str/0/str · returned Logger · level recorded 2026-09-25
unique in 30 papers mit_semseg/utils.py ran; the contract check could not run (RAISES) BSD-3-Clause (permissive) here; the stored copy is pointer only · 5feabe579b35978a · report fixture: signature ar:ndarray/1/int, return_index:bool/0/bool, return_inverse:bool/0/bool, return_counts:bool/0/bool · returned tuple · level recorded 2026-09-25
as_numpy in 12 papers mit_semseg/lib/utils/th.py unverified BSD-3-Clause (permissive) · c08e7121f699a983 · report
yuanyuanli85/tf-hrnet community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
add_layers net/utils.py ran BSD-3-Clause (permissive) · 0619db6c90ac8be6 · report fixture: signature origfeatures:dict/0/?, dwfeatrues:dict/0/?, upfeatures:dict/0/?, nums_output:int/0/int · returned list · level recorded 2026-09-24
create_downsample_fn_matrix net/utils.py ran BSD-3-Clause (permissive) · f6318bc574966adf · report fixture: signature num_branches:int/0/int, inputs:list/1/str, num_output_branches:int/0/int, output_channels:list/1/int · returned dict · level recorded 2026-09-24
create_upsample_fn_matrix net/utils.py ran BSD-3-Clause (permissive) · 0944678dd9feace7 · report fixture: signature num_branches:int/0/int, inputs:list/1/Tensor, num_output_branches:int/0/int, output_channels:list/1/int · returned dict · level recorded 2026-09-24
get_global_step_from_ckpt trainer/utils.py ran BSD-3-Clause (permissive) · 0db1a7c39ef342bb · report fixture: signature ckptpath:str/0/str · returned int · level recorded 2026-09-24
he_normal_fanout net/model.py ran BSD-3-Clause (permissive) · 963be56113879485 · report fixture: signature seed:NoneType/0/? · returned VarianceScaling · level recorded 2026-09-24
parse_example_proto datasets/ilsvrc12_dataset.py unverified BSD-3-Clause (permissive) · 31327aeaa8ee6db0 · report

Tasks

Dichotomous Image SegmentationFace AlignmentInstance SegmentationObject DetectionPose EstimationRepresentation LearningSemantic SegmentationThermal Image SegmentationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dichotomous Image Segmentation DIS-TE1 HRNet E-measure 0.797 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 HRNet HCE 262 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 HRNet MAE 0.088 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 HRNet S-Measure 0.742 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 HRNet max F-Measure 0.668 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 HRNet weighted F-measure 0.579 #11 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 HRNet E-measure 0.840 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 HRNet HCE 555 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 HRNet MAE 0.087 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 HRNet S-Measure 0.784 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 HRNet max F-Measure 0.747 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 HRNet weighted F-measure 0.664 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 HRNet E-measure 0.869 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 HRNet HCE 1049 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 HRNet MAE 0.080 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 HRNet S-Measure 0.805 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 HRNet max F-Measure 0.784 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 HRNet weighted F-measure 0.700 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 HRNet E-measure 0.854 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 HRNet HCE 3864 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 HRNet MAE 0.092 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 HRNet S-Measure 0.792 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 HRNet max F-Measure 0.772 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 HRNet weighted F-measure 0.687 #10 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD HRNet E-measure 0.824 #12 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD HRNet HCE 1560 #12 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD HRNet MAE 0.095 #12 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD HRNet S-Measure 0.767 #12 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD HRNet max F-Measure 0.726 #12 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD HRNet weighted F-measure 0.641 #12 of 24 Archive leaderboard report
Face Alignment 300W HRNet NME_inter-ocular (%, Challenge) 5.15 #25 of 48 Archive leaderboard report
Face Alignment 300W HRNet NME_inter-ocular (%, Common) 2.87 #25 of 48 Archive leaderboard report
Face Alignment 300W HRNet NME_inter-ocular (%, Full) 3.32 #25 of 48 Archive leaderboard report
Face Alignment COFW HRNet NME (inter-ocular) 3.45 #13 of 28 Archive leaderboard report
Face Alignment COFW-68 HRNetV2-W18 NME (inter-ocular) 5.06 #6 of 7 Archive leaderboard report
Face Alignment WFLW HRNet NME (inter-ocular) 4.60 #21 of 36 Archive leaderboard report
Instance Segmentation BDD100K val HRNet AP 22.5 #2 of 4 Archive leaderboard report
Instance Segmentation COCO minival HTC (HRNetV2p-W48) mask AP 41.0 #69 of 93 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W48) APL 62.2 #99 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W48) APM 50.3 #99 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W48) APS 28.8 #99 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W48) box AP 47.0 #99 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W48, cascade) APL 60.1 #109 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W48, cascade) APS 27.5 #109 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W48, cascade) box AP 46.0 #109 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W32) APL 59.5 #114 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W32) APM 48.4 #114 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W32) APS 27.0 #114 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W32) box AP 45.3 #114 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W48) AP50 62.7 #125 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W48) AP75 48.7 #125 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W48) APL 58.5 #125 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W48) APM 48.1 #125 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W48) APS 26.3 #125 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W48) box AP 44.6 #125 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W32) AP50 61.7 #137 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W32) AP75 47.7 #137 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W32) APL 57.4 #137 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W32) APM 46.5 #137 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W32) APS 25.6 #137 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W32) box AP 43.7 #137 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W18) APM 46.0 #145 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W18) APS 26.6 #145 of 220 Archive leaderboard report
Object Detection COCO minival HTC (HRNetV2p-W18) box AP 43.1 #145 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W32) APM 45.4 #156 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W32) APS 25.0 #156 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W32) box AP 42.3 #156 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W48) AP50 62.8 #160 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W48) AP75 45.9 #160 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W48) APL 54.6 #160 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W48) APM 44.7 #160 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W48) box AP 41.8 #160 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W18) AP50 59.2 #166 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W18) AP75 44.9 #166 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W18) APL 54.1 #166 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W18) APM 44.2 #166 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W18) APS 23.7 #166 of 220 Archive leaderboard report
Object Detection COCO minival Cascade R-CNN (HRNetV2p-W18) box AP 41.3 #166 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W32) AP50 61.8 #170 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W32) AP75 44.8 #170 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W32) APL 53.3 #170 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W32) APM 43.7 #170 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W32) APS 24.4 #170 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W32) box AP 40.9 #170 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W18) APL 51.0 #190 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W18) APM 41.7 #190 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W18) box AP 39.2 #190 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W18) AP50 58.9 #199 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W18) AP75 41.5 #199 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W18) APL 49.6 #199 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W18) APM 40.8 #199 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W18) APS 22.6 #199 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (HRNetV2p-W18) box AP 38.0 #199 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W32, cascade) APM 47.9 #218 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (HRNetV2p-W32, cascade) APS 26.1 #218 of 220 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) AP50 65.9 #119 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) AP75 51.2 #119 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) APL 59.8 #119 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) APM 49.7 #119 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) APS 28.0 #119 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) Hardware Burden 15G #119 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) Operations per network pass 71.7G #119 of 225 Archive leaderboard report
Object Detection COCO test-dev HTC (HRNetV2p-W48) box mAP 47.3 #119 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) AP50 64.0 #130 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) AP75 50.3 #130 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) APL 58.3 #130 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) APM 48.6 #130 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) APS 27.1 #130 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) Hardware Burden 15G #130 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) Operations per network pass 61.8G #130 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (HRNetV2p-W48 + cascade) box mAP 46.1 #130 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet (HRNetV2-W48) AP75 46.5 #158 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet (HRNetV2-W48) APL 57.8 #158 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet (HRNetV2-W48) APS 22.2 #158 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet (HRNetV2-W48) Hardware Burden 16G #158 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet (HRNetV2-W48) Operations per network pass 21.7G #158 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet (HRNetV2-W48) box mAP 43.5 #158 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) AP50 63.6 #174 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) AP75 46.4 #174 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) APL 53.0 #174 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) APM 44.6 #174 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) APS 24.9 #174 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) Hardware Burden 16G #174 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) Operations per network pass 20.8G #174 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN (HRNetV2p-W48) box mAP 42.4 #174 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNetV2p-W48) AP50 59.3 #193 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNetV2p-W48) APL 51.0 #193 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNetV2p-W48) APM 42.6 #193 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNetV2p-W48) APS 23.4 #193 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNetV2p-W48) Hardware Burden 16G #193 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNetV2p-W48) Operations per network pass 27.3G #193 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNetV2p-W48) box mAP 40.5 #193 of 225 Archive leaderboard report
Semantic Segmentation Cityscapes test HRNetV2 (train+val) Mean IoU (class) 81.6% #39 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes val HRNetV2 (HRNetV2-W48) mIoU 81.1 #45 of 99 Archive leaderboard report
Semantic Segmentation Cityscapes val HRNetV2 (HRNetV2-W40) mIoU 80.2 #55 of 99 Archive leaderboard report
Semantic Segmentation DADA-seg HRNet (ACDC) mIoU 27.5 #9 of 28 Archive leaderboard report
Semantic Segmentation PASCAL Context CFNet (ResNet-101) mIoU 54.0 #36 of 66 Archive leaderboard report
Semantic Segmentation PASCAL Context HRNetV2 HRNetV2-W48 mIoU 54 #37 of 66 Archive leaderboard report
Semantic Segmentation Potsdam HRNet-48 mIoU 84.22 #1 of 3 Archive leaderboard report
Semantic Segmentation Potsdam HRNet-18 mIoU 84.02 #2 of 3 Archive leaderboard report
Semantic Segmentation US3D HRNet-48 mIoU 72.66 #2 of 3 Archive leaderboard report
Semantic Segmentation US3D HRNet-18 mIoU 60.33 #3 of 3 Archive leaderboard report
Semantic Segmentation Vaihingen HRNet-48 mIoU 76.75 #8 of 13 Archive leaderboard report
Semantic Segmentation Vaihingen HRNet-18 mIoU 75.90 #10 of 13 Archive leaderboard report
Thermal Image Segmentation MFN Dataset HRNet mIOU 51.7 #40 of 55 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

Introduced by this paper: HRNet

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCascade Corner PoolingCascade R-CNNCenter PoolingCenterNetConvolutionDLAFaster R-CNNGlobal Average PoolingHRNetKaiming InitializationMask R-CNNMax PoolingRPNReLUResidual BlockResidual ConnectionRoIAlignRoIPoolSoftmax

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