</> Code with Papers by Syntology

Datasets › VGGFace2

VGGFace2 (Vggface2: A dataset for recognising faces across pose and age)

Introduced by Qiong Cao et al. in VGGFace2: A dataset for recognising faces across pose and age23 Oct 2017 archive 2025-07-28

VGGFace2 is a large-scale face recognition dataset. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession. VGGFace2 contains images from identities spanning a wide range of different ethnicities, accents, professions and ages. All face images are captured "in the wild", with pose and emotion variations and different lighting and occlusion conditions. Face distribution for different identities is varied, from 87 to 843, with an average of 362 images for each subject.

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Attribution VGGFace2 SMDL-Attribution (ICLR version) Insertion AUC score (ArcFace ResNet-101) 0.6705 Less is More: Fewer Interpretable Region via Submodular... ruoyuchen10/smdl-attribution 8 Compare
Image Super-Resolution VggFace2 - 8x upscaling Full-GWAInet PSNR 25.57 Exemplar Guided Face Image Super-Resolution without... berkdogan2/GWAInet 7 Compare
Facial Inpainting VggFace2 SymmFCNet (Full) PSNR 27.81 Learning Symmetry Consistent Deep CNNs for Face Completion csxmli2016/SymmFCNet 1 Compare

Papers archive 2025-07-28

16 shown of 16 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 539. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Less is More: Fewer Interpretable Region via Submodular Subset Selection 1 1 14 Feb 2024 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure 1 1 13 Jun 2022 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Exemplar Guided Face Image Super-Resolution without Facial Landmarks 1 1 17 Jun 2019 not harvested
Learning Symmetry Consistent Deep CNNs for Face Completion 1 1 19 Dec 2018 not harvested
RISE: Randomized Input Sampling for Explanation of Black-box Models 13 1 19 Jun 2018 ran 1 of 34 samples (33 unverified; 10 pointer-only for licence)
Learning Warped Guidance for Blind Face Restoration 1 1 13 Apr 2018 not harvested
Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution 0 1 1 Oct 2017 not harvested
Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by Transformative Discriminative Autoencoders 0 1 1 Jul 2017 not harvested
A Unified Approach to Interpreting Model Predictions 17 1 22 May 2017 ran 3 of 8 samples (5 unverified; 6 pointer-only for licence)
Axiomatic Attribution for Deep Networks 40 1 4 Mar 2017 ran 36 of 56 samples (20 unverified; 17 pointer-only for licence)
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization 126 1 7 Oct 2016 ran 79 of 141 samples (62 unverified; 68 pointer-only for licence)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network 140 1 15 Sep 2016 ran 16 of 72 samples (56 unverified; 11 pointer-only for licence)
Deep Cascaded Bi-Network for Face Hallucination 0 1 18 Jul 2016 not harvested
"Why Should I Trust You?": Explaining the Predictions of Any Classifier 27 1 16 Feb 2016 ran 5 of 19 samples (14 unverified)
Accurate Image Super-Resolution Using Very Deep Convolutional Networks 8 1 14 Nov 2015 ran 0 of 6 samples (6 unverified)
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps 23 1 20 Dec 2013 ran 1 of 4 samples (3 unverified; 1 pointer-only for licence)

Dataset loaders archive 2025-07-28

www.tensorflow.org/datasets/catalog/vgg_face2tensorflow/datasetstfjax

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Image Super-ResolutionFacial InpaintingImage Attribution

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

English

Variants archive 2025-07-28

  • VggFace2
  • VGGFace2 (2.3M)
  • VggFace2 - 8x upscaling
  • VGGFace2

4 variant names, as the archive lists them.

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