Papers › Teacher Supervises Students How to Learn From Partially Labeled Images for Facial...

Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection

6 Aug 2019ICCV 2019 10arXiv:1908.02116archive 2025-07-28

Xuanyi Dong, Yi Yang

Facial landmark detection aims to localize the anatomically defined points of human faces. In this paper, we study facial landmark detection from partially labeled facial images. A typical approach is to (1) train a detector on the labeled images; (2) generate new training samples using this detector's prediction as pseudo labels of unlabeled images; (3) retrain the detector on the labeled samples and partial pseudo labeled samples. In this way, the detector can learn from both labeled and unlabeled data to become robust. In this paper, we propose an interaction mechanism between a teacher and two students to generate more reliable pseudo labels for unlabeled data, which are beneficial to semi-supervised facial landmark detection. Specifically, the two students are instantiated as dual detectors. The teacher learns to judge the quality of the pseudo labels generated by the students and filter out unqualified samples before the retraining stage. In this way, the student detectors get feedback from their teacher and are retrained by premium data generated by itself. Since the two students are trained by different samples, a combination of their predictions will be more robust as the final prediction compared to either prediction. Extensive experiments on 300-W and AFLW benchmarks show that the interactions between teacher and students contribute to better utilization of the unlabeled data and achieves state-of-the-art performance.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1908.02116")

Code

Syntology Ran 1 of 9 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 1 ran; community (archive-listed): 6 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

D-X-Y/landmark-detection officialmentioned in papermentioned on GitHubpytorch report
D-X-Y/SAN mentioned on GitHubpytorchMIT 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

9 samples harvested; 1 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
8unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

get_name D-X-Y/landmark-detection/SRT/cache_data/GEN_300W.py official repository ran · our draft was wrong MIT (permissive) · e137aed896bedb2b · report
load_box D-X-Y/landmark-detection/SRT/cache_data/GEN_300W.py official repository unverified MIT (permissive) · ba02f21845e82025 · report
load_mats D-X-Y/landmark-detection/SRT/cache_data/GEN_300W.py official repository unverified MIT (permissive) · 4b61e25ba75a3aa6 · report
face_align D-X-Y/SAN/SAN/gen_mean_face.py community (archive-listed) unverified MIT (permissive) · 93b84997f1088de5 · report
load_all_300w D-X-Y/SAN/SAN/cache_data/generate_300W.py community (archive-listed) unverified MIT (permissive) · 35a75e51f1b18932 · report
load_box D-X-Y/SAN/SAN/cache_data/generate_300W.py community (archive-listed) unverified MIT (permissive) · b923e197278800b0 · report
load_mats D-X-Y/SAN/SAN/cache_data/generate_300W.py community (archive-listed) unverified MIT (permissive) · bdd903ed2401815b · report
normalize D-X-Y/SAN/SAN/gen_mean_face.py community (archive-listed) unverified MIT (permissive) · 8d962e105ab61b33 · report
np2variable D-X-Y/SAN/SAN/gen_mean_face.py community (archive-listed) unverified MIT (permissive) · 5cd8c08f75d5eeb9 · report

Tasks

Facial Landmark Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Facial Landmark Detection 300W TS3 NME 3.49 #10 of 15 Archive leaderboard report
Facial Landmark Detection 300W (Full) TS3 Mean NME 3.49 #1 of 2 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