Papers › VGGFace2: A dataset for recognising faces across pose and age

VGGFace2: A dataset for recognising faces across pose and age

23 Oct 2017arXiv:1710.08092archive 2025-07-28

Qiong Cao, Li Shen, Weidi Xie, Omkar M. Parkhi, Andrew Zisserman

In this paper, we introduce a new large-scale face dataset named VGGFace2. The dataset contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession (e.g. actors, athletes, politicians). The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimize the label noise. We describe how the dataset was collected, in particular the automated and manual filtering stages to ensure a high accuracy for the images of each identity. To assess face recognition performance using the new dataset, we train ResNet-50 (with and without Squeeze-and-Excitation blocks) Convolutional Neural Networks on VGGFace2, on MS- Celeb-1M, and on their union, and show that training on VGGFace2 leads to improved recognition performance over pose and age. Finally, using the models trained on these datasets, we demonstrate state-of-the-art performance on all the IARPA Janus face recognition benchmarks, e.g. IJB-A, IJB-B and IJB-C, exceeding the previous state-of-the-art by a large margin. Datasets and models are publicly available.

PaperPDFCodeCode 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 8 code samples harvested from 3 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 3 repositories, 5 ran (1 with no instrument failure; 4 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 6 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 5 samples that ran has no recorded date.

24 repositories listed; official and paper-mentioned ones first.

394781865/insightface mentioned on GitHubtfMITSyntology: not harvested report
AmirSh15/FECNet mentioned on GitHubpytorchSyntology: not harvested report
Dou-Yu-xuan/vggface2-pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
NetoPedro/VGGFace2-Test mentioned on GitHubSyntology: not harvested report
TreB1eN/InsightFace_Pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices (arXiv:1804.07573; that paper's own run record: 33 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 5 honoured, 0 violated, 19 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
WeidiXie/Keras-VGGFace2-ResNet50 mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
YadiraF/DECA mentioned on GitHubpytorchSyntology: not harvested report
afrazsalim/WebBasedGameWithNodeJs mentioned on GitHubtfSyntology: not harvested report
albanie/mcnCrossModalEmotions mentioned on GitHubpytorchMITSyntology: not harvested report
chenggongliang/arcface mentioned on GitHubmxnetMITSyntology: not harvested report
cvtower/seesawfacenet_pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SeesawFaceNets: sparse and robust face verification model for mobile platform (arXiv:1908.09124; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
cydonia999/VGGFace2-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
deepinsight/insightface mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data (arXiv:2601.07576; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
dooleys/fr-nas mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Learning Face Attributes in the Wild (arXiv:1411.7766; that paper's own run record: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified) and Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition (arXiv:2210.09943; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
eric-erki/insightface mentioned on GitHubtfMITSyntology: not harvested report
fvmassoli/mafer-multires-facial-expression-recognition mentioned on GitHubpytorchSyntology: not harvested report
sunil-rival/insightface mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices (arXiv:1804.07573; that paper's own run record: 33 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 5 honoured, 0 violated, 19 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
tamerthamoqa/facenet-pytorch-glint360k mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FaceNet: A Unified Embedding for Face Recognition and Clustering (arXiv:1503.03832; that paper's own run record: 99 ran (of which 19 constructed an object rather than computing a result; 83 with no instrument failure: 11 honoured, 11 violated, 61 with no contract checked; 16 where Syntology's instrument failed) · 55 unverified); nothing checks that they implement this paper's method. report
yfeng95/deca mentioned on GitHubpytorchSyntology: not harvested report
zrui94/insight_mx mentioned on GitHubtfSyntology: 3 samples, 3 ran (2 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

8 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
1ran · our draft was wrong
3ran; the contract check could not run
3unverified

Licence: 6 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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.

Dou-Yu-xuan/vggface2-pytorch community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
conv3x3 in 1,376 papers models/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
get_id_label_map utils.py unverified MIT (permissive) · 50ddbc18350aeba1 · report
WeidiXie/Keras-VGGFace2-ResNet50 community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
verification src/predict.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 2d91d93f4e37792a · report fixture: signature unique_templates:ndarray/1/int, tmp_feats:ndarray/2/float, p1:ndarray/1/int, p2:ndarray/1/int · returned ndarray · level recorded 2026-09-22
template_encoding src/predict.py unverified no licence file found · pointer only · 534645843fb57c75 · report
zrui94/insight_mx community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
calculate_accuracy in 65 papers src/eval/verification.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · f975336b5d5f1a80 · report fixture: signature threshold:float/0/float, dist:ndarray/1/float, actual_issame:ndarray/1/bool · returned tuple · level recorded 2026-09-22
calculate_roc in 14 papers src/eval/verification.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence of this copy not recorded · db4008738f6c3eae · report fixture: signature thresholds:ndarray/1/float, embeddings1:ndarray/2/float, embeddings2:ndarray/2/float, actual_issame:ndarray/1/bool, nrof_folds:int/0/int, pca:int/0/int · returned tuple · level recorded 2026-09-22
calculate_val in 8 papers src/eval/verification.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · c7c89ea2508beb10 · report fixture: signature thresholds:ndarray/1/float, embeddings1:ndarray/2/float, embeddings2:ndarray/2/float, actual_issame:ndarray/1/bool, far_target:float/0/float, nrof_folds:int/0/int · returned tuple · level recorded 2026-09-22

Tasks

Face RecognitionFace VerificationImage Retrieval

Datasets

Introduced by this paper, per the archive.

VGG-Face2VGGFace2VGGFace2 Dataset

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Verification IJB-A VGGFace2_ft TAR @ FAR=0.001 92.1 #5 of 17 Archive leaderboard report
Face Verification IJB-A VGGFace2_ft TAR @ FAR=0.01 96.8% #5 of 17 Archive leaderboard report
Face Verification IJB-A VGGFace2_ft TAR @ FAR=0.1 0.99 #5 of 17 Archive leaderboard report
Face Verification IJB-B VGGFace2_ft TAR @ FAR=0.001 90.8 #7 of 12 Archive leaderboard report
Face Verification IJB-B VGGFace2_ft TAR @ FAR=0.01 95.6% #7 of 12 Archive leaderboard report
Face Verification IJB-C VGGFace2_ft TAR @ FAR=1e-2 96.7% #23 of 26 Archive leaderboard report
Face Verification IJB-C VGGFace2_ft TAR @ FAR=1e-3 92.7% #23 of 26 Archive leaderboard report
Face Verification IJB-C VGGFace2_ft model R50 #23 of 26 Archive leaderboard report
Face Verification IJB-C VGGFace2_ft training dataset Vggface2 #23 of 26 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