Benjamin Graham

Benjamin Graham joined Facebook AI Research (FAIR) as a Research Scientist in July 2016. Benjamin studied mathematics, and in particular, probability theory relating to spatial phenomenon as an undergraduate at Oxford University. As a PhD student at Cambridge University he was supervised by Professor Geoffrey Grimmett and received his postdoc at UBC Vancouver and ENS Paris. Whilst working in the Department of Statistics at the University of Warwick, Benjamin became interested in machine learning and took part in a few Kaggle competitions.

Benjamin's Publications

April 25, 2020

RESEARCH

ML APPLICATIONS

And the bit goes down: Revisiting the quantization of neural networks

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather…

Pierre Stock, Armand Joulin, Remi Gribonval, Benjamin Graham, Hervé Jégou

April 25, 2020

September 05, 2019

RESEARCH

ML APPLICATIONS

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

We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for…

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

September 05, 2019

June 18, 2018

RESEARCH

COMPUTER VISION

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally…

Benjamin Graham, Laurens van der Maaten, Martin Engelcke

June 18, 2018

May 05, 2019

RESEARCH

ML APPLICATIONS

Equi-normalization of Neural Networks

Modern neural networks are over-parametrized. In particular, each rectified linear hidden unit can be modified by a multiplicative factor by adjusting input and output weights, without changing the rest of the network. Inspired by the…

Pierre Stock, Benjamin Graham, Rémi Gribonval, Hervé Jégou

May 05, 2019