Visual Geometry Group
lastmod 2026-11-10created 2016-03-103 edits
Visual Geometry Group (VGG) is a computer vision research group in the Department of Engineering Science at the University of Oxford. It is widely known for the paper "Very Deep Convolutional Networks for Large-Scale Image Recognition", which proposed the VGG16 and VGG19 networks built by stacking deep layers of 3×3 convolutions. These models placed at the top in ILSVRC 2014 and were later widely used as a standard backbone for transfer learning and feature extraction.
Visual Geometry Group.
Very Deep Convolutional Networks for Large-Scale Image Recognition
- Visual Geometry Group - Department of Engineering Science, University of Oxford - Very Deep Convolutional Networks for Large-Scale Visual Recognition
- arXiv.org > cs > arXiv:1409.1556