Papers › Style Aggregated Network for Facial Landmark Detection

Style Aggregated Network for Facial Landmark Detection

12 Mar 2018CVPR 2018 6arXiv:1803.04108archive 2025-07-28

Xuanyi Dong, Yan Yan, Wanli Ouyang, Yi Yang

Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the variance of faces themselves, the intrinsic variance of image styles, e.g., grayscale vs. color images, light vs. dark, intense vs. dull, and so on, has constantly been overlooked. This issue becomes inevitable as increasing web images are collected from various sources for training neural networks. In this work, we propose a style-aggregated approach to deal with the large intrinsic variance of image styles for facial landmark detection. Our method transforms original face images to style-aggregated images by a generative adversarial module. The proposed scheme uses the style-aggregated image to maintain face images that are more robust to environmental changes. Then the original face images accompanying with style-aggregated ones play a duet to train a landmark detector which is complementary to each other. In this way, for each face, our method takes two images as input, i.e., one in its original style and the other in the aggregated style. In experiments, we observe that the large variance of image styles would degenerate the performance of facial landmark detectors. Moreover, we show the robustness of our method to the large variance of image styles by comparing to a variant of our approach, in which the generative adversarial module is removed, and no style-aggregated images are used. Our approach is demonstrated to perform well when compared with state-of-the-art algorithms on benchmark datasets AFLW and 300-W. Code is publicly available on GitHub: https://github.com/D-X-Y/SAN

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

D-X-Y/SAN officialmentioned in paperpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Teacher Supervises Students How to Learn From Partially Labeled Images for Facial... (arXiv:1908.02116; 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) · 7 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

Face AlignmentFacial Landmark Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Alignment 300W SAN NME_inter-ocular (%, Challenge) 6.60 #36 of 48 Archive leaderboard report
Face Alignment 300W SAN NME_inter-ocular (%, Common) 3.34 #36 of 48 Archive leaderboard report
Face Alignment 300W SAN NME_inter-ocular (%, Full) 3.98 #36 of 48 Archive leaderboard report
Face Alignment AFLW-19 SAN AUC_box@0.07 (%, Full) 54.0 #17 of 23 Archive leaderboard report
Face Alignment AFLW-19 SAN NME_box (%, Full) 4.04 #17 of 23 Archive leaderboard report
Face Alignment AFLW-19 SAN NME_diag (%, Frontal) 1.85 #17 of 23 Archive leaderboard report
Face Alignment AFLW-19 SAN NME_diag (%, Full) 1.91 #17 of 23 Archive leaderboard report
Facial Landmark Detection 300W SAN GT NME 3.98 #11 of 15 Archive leaderboard report
Facial Landmark Detection AFLW-Front SAN Mean NME 1.85 #3 of 3 Archive leaderboard report
Facial Landmark Detection AFLW-Full SAN Mean NME 1.91 #3 of 5 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