Vggface2: A dataset for recognising faces across pose and age
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.
Variants: VggFace2, VGGFace2 (2.3M), VggFace2 - 8x upscaling, VGGFace2
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Attribution | SMDL-Attribution (ICLR version) | Less is More: Fewer Interpretable … | 2024-02-14 |
| Image Attribution | HSIC-Attribution | Making Sense of Dependence: Efficient … | 2022-06-13 |
| Image Attribution | RISE | RISE: Randomized Input Sampling for … | 2018-06-19 |
| Image Attribution | Kernel SHAP | A Unified Approach to Interpreting … | 2017-05-22 |
| Image Attribution | Integrated Gradients | Axiomatic Attribution for Deep Networks | 2017-03-04 |
| Image Attribution | Grad-CAM | Grad-CAM: Visual Explanations from Deep … | 2016-10-07 |
| Image Attribution | LIME | "Why Should I Trust You?": … | 2016-02-16 |
| Image Attribution | Saliency | Deep Inside Convolutional Networks: Visualising … | 2013-12-20 |
Recent papers with results on this dataset: