Papers › Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

16 Apr 2019ICCV 2019 10arXiv:1904.07399archive 2025-07-28

Xinyao Wang, Liefeng Bo, Li Fuxin

Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap regression is rarely studied. In this paper, we analyze the ideal loss function properties for heatmap regression in face alignment problems. Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels. This adaptability penalizes loss more on foreground pixels while less on background pixels. To address the imbalance between foreground and background pixels, we also propose Weighted Loss Map, which assigns high weights on foreground and difficult background pixels to help training process focus more on pixels that are crucial to landmark localization. To further improve face alignment accuracy, we introduce boundary prediction and CoordConv with boundary coordinates. Extensive experiments on different benchmarks, including COFW, 300W and WFLW, show our approach outperforms the state-of-the-art by a significant margin on various evaluation metrics. Besides, the Adaptive Wing loss also helps other heatmap regression tasks. Code will be made publicly available at https://github.com/protossw512/AdaptiveWingLoss.

PaperPDFConference PDFCodeCode 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 27 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 21 samples from 2 repositories, 15 ran (8 with no instrument failure; 7 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 2 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 17 samples that ran has no recorded date.

protossw512/AdaptiveWingLoss officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
affromero/SMILE mentioned on GitHubpytorchMITSyntology: 20 samples, 14 ran (6 instrument-failed) · 6 unverified report
emilianavt/OpenSeeFace mentioned on GitHubtfBSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Searching for MobileNetV3 (arXiv:1905.02244; that paper's own run record: 86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 9 honoured, 2 violated, 64 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified); nothing checks that they implement this paper's method. report
mikgur/MADE_CV_1000_facial_landmarks mentioned on GitHubpytorchSyntology: not harvested report
ttruty/facial-feature-mouse-control mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
zs7779/FAN_AdaptiveWingLoss mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 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

27 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 10 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.

7ran · our draft was wrong
10ran
10unverified

Licence: 7 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

protossw512/AdaptiveWingLoss official repository 6 samples, 2 ran (0 instrument-failed) · 4 unverified
cv_crop utils/utils.py ran Apache-2.0 (permissive) · 70a97576b2e259bc · report fixture: signature image:ndarray/3/int, landmarks:ndarray/2/float, center:list/1/float, scale:float/0/float, resolution:int/0/int, center_shift:int/0/int · returned tuple · level recorded 2026-09-25
load_meta_subset_data dataset/convert_WFLW.py ran Apache-2.0 (permissive) · 0ef7e489513c369c · report fixture: signature meta_path:str/0/str · returned list · level recorded 2026-09-25
draw_gaussian in 5 papers utils/utils.py unverified Apache-2.0 (permissive) · d5a717a5a0d0df17 · report
parse_pts dataset/convert_WFLW.py unverified Apache-2.0 (permissive) · b26af76575924632 · report
affromero/SMILE community (archive-listed) 20 samples, 14 ran (6 instrument-failed) · 6 unverified
bisenet2sean metrics/segmentation_model.py ran MIT (permissive) · e47699a7d59b856e · report fixture: signature label:Tensor/2/int, reverse:bool/0/bool · returned Tensor · level recorded 2026-09-24
conv3x3 in 1,376 papers metrics/arcface_resnet.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
conv_1x1_bn in 59 papers metrics/mobilenetv2.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · a0131fb70c267a9e · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-22
conv_3x3_bn in 21 papers metrics/mobilenetv2.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 408e747e0425a594 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
create_layer_basic in 19 papers metrics/segmentation_model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 325b8d54f52e2421 · report fixture: signature in_chan:int/0/int, out_chan:int/0/int, bnum:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-24
gan_feat_loss misc/losses.py ran MIT (permissive) · d27b2e2462c936f0 · report fixture: signature real_feat:list/1/Tensor, fake_feat:list/1/Tensor · returned Tensor · level recorded 2026-09-24
get_activations in 100 papers metrics/fid_score.py ran MIT (permissive) · 914550130b4d8353 · report fixture: signature images:ndarray/4/float, model:callable/0/?, batch_size:int/0/int, dims:int/0/int, cuda:bool/0/bool, verbose:bool/0/bool · returned ndarray · level recorded 2026-09-24
get_disc misc/losses.py ran MIT (permissive) · 4566e5df584812fa · report fixture: signature Disc:callable/0/?, input:Tensor/2/float, label:Tensor/2/float, seg:Tensor/2/float · returned tuple · level recorded 2026-09-24
get_images in 21 papers metrics/fid_score.py ran MIT (permissive) · 608139996fc77fef · report fixture: signature images:list/1/str, start:int/0/int, end:int/0/int · returned ndarray · level recorded 2026-09-24
get_zero_tensor misc/losses.py ran fingerprinted MIT (permissive) · 74b3e6d3ba3df864 · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-24
process_image in 43 papers metrics/identity_model.py ran fingerprinted MIT (permissive) · 011d1c9dcf2417ee · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-24
resnet18 in 432 papers metrics/arcface_resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · bd8fb5c95fa87652 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-22
resnet34 in 148 papers metrics/arcface_resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · bb357f89cac141ff · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-22
toGray metrics/identity_model.py ran fingerprinted MIT (permissive) · 32fe5c39d154aeef · report fixture: signature tensor:Tensor/4/float · returned Tensor · level recorded 2026-09-24
calculate_frechet_distance in 119 papers metrics/fid_score.py unverified MIT (permissive) · 0def50a351111624 · report
compute_f1 in 40 papers metrics/f1_score.py unverified MIT (permissive) · cf6388d3dfe650b4 · report
get_loader in 62 papers data_loader.py unverified MIT (permissive) · 2cef682f544273a6 · report
get_transformations data_loader.py unverified MIT (permissive) · 24d857446f68d11f · report
mobilenetv2 in 7 papers metrics/mobilenetv2.py unverified MIT (permissive) · 44d3e225af74f1a4 · report
update_config in 54 papers config.py unverified MIT (permissive) · e0e9e48345e57d40 · report
zs7779/FAN_AdaptiveWingLoss community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
conv3x3 in 1,376 papers core/models.py ran · our draft was wrong no licence file found · pointer only · cd28335574411d48 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, strd:int/0/int, padding:int/0/int, bias:bool/0/bool, dilation:int/0/int · returned Conv2d · level recorded 2026-09-22

Tasks

Face AlignmentRobust Face Alignmentregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Alignment 300W AWing NME_inter-ocular (%, Challenge) 4.52 #11 of 48 Archive leaderboard report
Face Alignment 300W AWing NME_inter-ocular (%, Common) 2.72 #11 of 48 Archive leaderboard report
Face Alignment 300W AWing NME_inter-ocular (%, Full) 3.07 #11 of 48 Archive leaderboard report
Face Alignment 300W AWing NME_inter-pupil (%, Challenge) 6.52 #11 of 48 Archive leaderboard report
Face Alignment 300W AWing NME_inter-pupil (%, Common) 3.77 #11 of 48 Archive leaderboard report
Face Alignment 300W AWing NME_inter-pupil (%, Full) 4.31 #11 of 48 Archive leaderboard report
Face Alignment WFLW AWing AUC@10 (inter-ocular) 57.19 #16 of 36 Archive leaderboard report
Face Alignment WFLW AWing FR@10 (inter-ocular) 2.84 #16 of 36 Archive leaderboard report
Face Alignment WFLW AWing NME (inter-ocular) 4.36 #16 of 36 Archive leaderboard report
Face Alignment WFW (Extra Data) Awing AUC@10 (inter-ocular) 57.19 #8 of 11 Archive leaderboard report
Face Alignment WFW (Extra Data) Awing FR@10 (inter-ocular) 2.84 #8 of 11 Archive leaderboard report
Face Alignment WFW (Extra Data) Awing NME (inter-ocular) 4.36 #8 of 11 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

CoordConvHeatmap

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