Papers › Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

17 Nov 2017CVPR 2018 6arXiv:1711.06753archive 2025-07-28

Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber, Xiao-Jun Wu

We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these loss functions suggests that, for the training of a CNN-based localisation model, more attention should be paid to small and medium range errors. To this end, we design a piece-wise loss function. The new loss amplifies the impact of errors from the interval (-w, w) by switching from L1 loss to a modified logarithm function. To address the problem of under-representation of samples with large out-of-plane head rotations in the training set, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation approaches. Last, the proposed approach is extended to create a two-stage framework for robust facial landmark localisation. The experimental results obtained on AFLW and 300W demonstrate the merits of the Wing loss function, and prove the superiority of the proposed method over the state-of-the-art approaches.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

mikgur/MADE_CV_1000_facial_landmarks mentioned on GitHubpytorchSyntology: not harvested report
mktoid/made-thousand-facial-landmarks mentioned on GitHubpytorchSyntology: not harvested report
noelmat/facelandmarks_wingloss mentioned on GitHubSyntology: not harvested report
parthapratimbanik/facial-keypoint-detection-udacity-ppb mentioned on GitHubpytorchMITSyntology: not harvested report
xialuxi/arcface-caffe mentioned on GitHubSyntology: 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

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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationFace Alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Alignment 300W Wing NME_inter-pupil (%, Challenge) 7.18 #47 of 48 Archive leaderboard report
Face Alignment 300W Wing NME_inter-pupil (%, Common) 3.27 #47 of 48 Archive leaderboard report
Face Alignment 300W Wing NME_inter-pupil (%, Full) 4.04 #47 of 48 Archive leaderboard report
Face Alignment AFLW-19 Wing AUC_box@0.07 (%, Full) 53.5 #14 of 23 Archive leaderboard report
Face Alignment AFLW-19 Wing NME_box (%, Full) 3.56 #14 of 23 Archive leaderboard report
Face Alignment AFLW-19 Wing NME_diag (%, Full) 1.65 #14 of 23 Archive leaderboard report
Face Alignment COFW Wing (Feng et al., 2018) NME (inter-ocular) 5.07 #20 of 28 Archive leaderboard report
Face Alignment WFLW Wing AUC@10 (inter-ocular) 55.4 #27 of 36 Archive leaderboard report
Face Alignment WFLW Wing FR@10 (inter-ocular) 6.00 #27 of 36 Archive leaderboard report
Face Alignment WFLW Wing NME (inter-ocular) 5.11 #27 of 36 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections