Papers › When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

13 May 2021CVPR 2021 1arXiv:2105.06152archive 2025-07-28

Jiahang Wang, Sheng Jin, Wentao Liu, Weizhong Liu, Chen Qian, Ping Luo

Human pose estimation is a fundamental yet challenging task in computer vision, which aims at localizing human anatomical keypoints. However, unlike human vision that is robust to various data corruptions such as blur and pixelation, current pose estimators are easily confused by these corruptions. This work comprehensively studies and addresses this problem by building rigorous robust benchmarks, termed COCO-C, MPII-C, and OCHuman-C, to evaluate the weaknesses of current advanced pose estimators, and a new algorithm termed AdvMix is proposed to improve their robustness in different corruptions. Our work has several unique benefits. (1) AdvMix is model-agnostic and capable in a wide-spectrum of pose estimation models. (2) AdvMix consists of adversarial augmentation and knowledge distillation. Adversarial augmentation contains two neural network modules that are trained jointly and competitively in an adversarial manner, where a generator network mixes different corrupted images to confuse a pose estimator, improving the robustness of the pose estimator by learning from harder samples. To compensate for the noise patterns by adversarial augmentation, knowledge distillation is applied to transfer clean pose structure knowledge to the target pose estimator. (3) Extensive experiments show that AdvMix significantly increases the robustness of pose estimations across a wide range of corruptions, while maintaining accuracy on clean data in various challenging benchmark datasets.

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

Syntology 25 code samples harvested from 4 repositories linked to this paper: 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. Where Syntology's instrument failed: 3 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 6 ran (1 with no instrument failure; 5 where Syntology's instrument failed); found in paper text by Syntology: 13 samples from 3 repositories, 8 ran (6 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.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 14 samples that ran has no recorded date.

AIprogrammer/AdvMix officialmentioned on GitHubpytorchSyntology: 12 samples, 6 ran (5 instrument-failed) · 6 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.

Code Syntology ran Syntology

25 samples harvested: 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. “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.

3ran · our draft was wrong
4ran; the contract check could not run
7ran
11unverified

Licence: 4 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

AIprogrammer/AdvMix official repository 12 samples, 6 ran (5 instrument-failed) · 6 unverified
AverageMeter in 26 papers lib/core/function.py ran MIT (permissive) · a605a498a2198a9d · report fixture: returned AverageMeter · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
lib/core/function.py ran · our draft was wrong MIT (permissive) · b44324561953846f · report fixture: signature outputs:Tensor/4/float, target:Tensor/4/float, hm_type:str/0/str, thr:float/0/float, args:NoneType/0/?, cfg:NoneType/0/? · returned tuple · level recorded 2026-09-22
calc_dists in 7 papers lib/core/function.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · b91b38261b03587d · report fixture: signature preds:ndarray/3/float, target:ndarray/3/float, normalize:ndarray/1/float · returned ndarray · level recorded 2026-09-22
dist_acc in 7 papers lib/core/function.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 1c2da88027e6e151 · report fixture: signature dists:ndarray/1/float, thr:float/0/float · returned float64 · level recorded 2026-09-22
tensor2im in 30 papers lib/core/function.py ran · our draft was wrong MIT (permissive) · dfdeea3ebb13fa9a · report fixture: returned ndarray · level recorded 2026-09-22
tofloat lib/core/function.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 599ce919c4b5d898 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
inv_coord_norm lib/core/function.py unverified MIT (permissive) · 73cacfdb88d0d0fb · report
save_batch_heatmaps lib/core/function.py unverified MIT (permissive) · 140dbadc1db1bd99 · report
save_batch_image_with_joints lib/core/function.py unverified MIT (permissive) · ee768f095e08626d · report
save_debug_images lib/core/function.py unverified MIT (permissive) · 98ce27ca4d149960 · report
set_require_grad lib/core/function.py unverified MIT (permissive) · 1a2ff0244d9cdfcf · report
train_advmix lib/core/function.py unverified MIT (permissive) · a63f8ab8d7310adb · report
leoxiaobin/deep-high-resolution-net.pytorch found in paper text by Syntology 4 samples, 3 ran (1 instrument-failed) · 1 unverified
box_to_center_scale demo/inference.py ran MIT (permissive) · 192666724266ef19 · report fixture: signature box:list/1/tuple, model_image_width:int/0/int, model_image_height:int/0/int · returned tuple · level recorded 2026-09-26
get_max_preds in 8 papers lib/core/inference.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted MIT (permissive) · 55c58ef5f795e3d1 · report fixture: signature batch_heatmaps:ndarray/4/float · returned tuple · level recorded 2026-09-22
get_person_detection_boxes demo/inference.py ran MIT (permissive) · 74bb768e238398b0 · report fixture: signature model:callable/0/?, img:ndarray/3/int, threshold:float/0/float · returned list · level recorded 2026-09-25
get_pose_net in 15 papers lib/models/pose_hrnet.py unverified MIT (permissive) · 2534c81208f21998 · report
vita-epfl/openpifpaf found in paper text by Syntology 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Laplace in 5 papers src/openpifpaf/network/losses/components.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 6c2047eb02f90875 · report fixture: signature x1:Tensor/1/float, x2:Tensor/1/float, logb:Tensor/1/float, t1:Tensor/1/float, t2:Tensor/1/float, bmin:Tensor/1/float · returned Tensor · level recorded 2026-09-22
SoftClamp src/openpifpaf/network/losses/components.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · d948ea963b20bbdc · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
HRNet/HigherHRNet-Human-Pose-Estimation found in paper text by Syntology 7 samples, 3 ran (1 instrument-failed) · 4 unverified
aggregate_results in 8 papers lib/core/inference.py ran MIT (permissive) · b2deafbfd7c1f3fc · report fixture: signature cfg:MockConfig/0/?, scale_factor:int/0/int, final_heatmaps:Tensor/4/float, tags_list:list/1/empty, heatmaps:list/1/Tensor, tags:list/1/Tensor · returned tuple · level recorded 2026-09-25
conv3x3 in 1,376 papers lib/models/pose_higher_hrnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is 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
make_input in 6 papers lib/core/loss.py ran MIT (permissive) here; the stored copy is pointer only · cdea90667046c71c · report fixture: signature t:Tensor/2/float, requires_grad:bool/0/bool, need_cuda:bool/0/bool · returned Tensor · level recorded 2026-09-24
build_dataset in 151 papers lib/dataset/build.py unverified MIT (permissive) · 0ff31375e05cb70d · report
get_pose_net in 15 papers lib/models/pose_higher_hrnet.py unverified MIT (permissive) · b1587fcc78f6fa72 · report
make_dataloader in 18 papers lib/dataset/build.py unverified MIT (permissive) · df9c22deab975625 · report
make_test_dataloader lib/dataset/build.py unverified MIT (permissive) · a4025bf00b852a33 · 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 AdvMix (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for AdvMix (graph method: AdvMix). 13 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. train_advmix entry · level 0 · unverified · a63f8ab8d7310adb
  2. AverageMeter helper · level 1 · ran · a605a498a2198a9d
  3. accuracy helper · level 1 · ran · our draft was wrong · b44324561953846f
  4. save_debug_images helper · level 0 · unverified · 98ce27ca4d149960
  5. set_require_grad helper · level 0 · unverified · 1a2ff0244d9cdfcf
  6. calc_dists helper · level 1 · ran; the contract check could not run (RAISES) · b91b38261b03587d
  7. dist_acc helper · level 1 · ran; the contract check could not run (RAISES) · 1c2da88027e6e151
  8. get_max_preds helper · level 1 · ran; the contract check could not run (RAISES) · 55c58ef5f795e3d1
  9. inv_coord_norm helper · level 0 · unverified · 73cacfdb88d0d0fb
  10. save_batch_heatmaps helper · level 0 · unverified · 140dbadc1db1bd99
  11. save_batch_image_with_joints helper · level 0 · unverified · ee768f095e08626d
  12. tofloat helper · level 1 · ran; the contract check could not run (RAISES) · 599ce919c4b5d898
  13. tensor2im helper · level 1 · ran · our draft was wrong · dfdeea3ebb13fa9a

harvested Assembly for AdvMix (graph method: AdvMix). 2 bricks; individually on a fixture: 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) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Laplace entry · level 1 · ran · 6c2047eb02f90875
  2. SoftClamp helper · level 1 · ran · d948ea963b20bbdc

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="2105.06152") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Knowledge DistillationPose Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge Distillation

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