Andrea Vedaldi

Research Scientist

I am a research scientist at Facebook AI Research since September 2018, with a focus on computer vision and machine learning. I am also Associate Professor at the University of Oxford, specialising on the same topics.


I am interested in deep image representations for computer vision, with applications to image understanding and 3D reconstruction. I am also interested in unsupervised learning and in the interpretability of black box models.

Related Links


Latest Publications

Transferring Dense Pose to Proximal Animal Classes

Artsiom Sanakoyeu, Vasil Khalidov, Maureen S. McCarthy, Andrea Vedaldi, Natalia Neverova

CVPR - May 31, 2020

Fixing the train-test resolution discrepancy

Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou

NeurIPS - December 9, 2019

Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels

Natalia Neverova, David Novotny, Andrea Vedaldi

NeurIPS - November 17, 2019

Understanding Deep Networks via Extremal Perturbations and Smooth Masks

Ruth Fong, Mandela Patrick, Andrea Vedaldi

ICCV - October 20, 2019

Occlusions for Effective Data Augmentation in Image Classification

Ruth Fong, Andrea Vedaldi

ICCV Workshop on Interpreting and Explaining Visual AI Models - October 20, 2019

C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion

David Novotny, Nikhila Ravi, Benjamin Graham, Natalia Neverova, Andrea Vedaldi

ICCV - September 5, 2019

Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cues

Natalia Neverova, James Thewlis, Riza Alp Guler, Iasonas Kokkinos, Andrea Vedaldi

CVPR - June 9, 2019