Papers › Pre-training strategies and datasets for facial representation learning

Pre-training strategies and datasets for facial representation learning

30 Mar 2021arXiv:2103.16554archive 2025-07-28

Adrian Bulat, Shiyang Cheng, Jing Yang, Andrew Garbett, Enrique Sanchez, Georgios Tzimiropoulos

What is the best way to learn a universal face representation? Recent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e.g. face recognition, facial landmark localization etc.) but has overlooked the overarching question of how to find a facial representation that can be readily adapted to several facial analysis tasks and datasets. To this end, we make the following 4 contributions: (a) we introduce, for the first time, a comprehensive evaluation benchmark for facial representation learning consisting of 5 important face analysis tasks. (b) We systematically investigate two ways of large-scale representation learning applied to faces: supervised and unsupervised pre-training. Importantly, we focus our evaluations on the case of few-shot facial learning. (c) We investigate important properties of the training datasets including their size and quality (labelled, unlabelled or even uncurated). (d) To draw our conclusions, we conducted a very large number of experiments. Our main two findings are: (1) Unsupervised pre-training on completely in-the-wild, uncurated data provides consistent and, in some cases, significant accuracy improvements for all facial tasks considered. (2) Many existing facial video datasets seem to have a large amount of redundancy. We will release code, and pre-trained models to facilitate future research.

PaperPDFCode

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

1adrianb/unsupervised-face-representation officialpytorchSyntology: not harvested report
tomas-gajarsky/facetorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaFace: Quality Adaptive Margin for Face Recognition (arXiv:2204.00964; that paper's own run record: 17 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified) and Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit... (arXiv:2205.01782; that paper's own run record: 7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 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

3D Face Reconstruction3D Facial Landmark LocalizationArousal EstimationEmotion RecognitionFace AlignmentFace RecognitionFacial Action Unit DetectionFacial Expression Recognition (FER)Few-Shot LearningRepresentation LearningUnsupervised Pre-trainingValence Estimation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction AFLW2000-3D VGG-F Mean NME 3.42% #2 of 8 Archive leaderboard report
Face Alignment AFLW-19 VGG-F NME_diag (%, Full) 1.55 #10 of 23 Archive leaderboard report
Face Alignment COFW Ours (VGG-F) NME (inter-ocular) 3.32 #10 of 28 Archive leaderboard report
Face Alignment WFW (Extra Data) VGG-F NME (inter-ocular) 4.57 #11 of 11 Archive leaderboard report
Facial Expression Recognition (FER) BP4D Ours (VGG-F) ICC 0.719 #2 of 2 Archive leaderboard report
Facial Expression Recognition (FER) DISFA Ours (VGG-F) ICC 0.598 #2 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