LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference

11 code implementations • ICCV 2021 • Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou, Matthijs Douze

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime.

General Classification Image Classification

Sparse 3D convolutional neural networks

2 code implementations • 12 May 2015 • Ben Graham

We have implemented a convolutional neural network designed for processing sparse three-dimensional input data.

3D Object Recognition Temporal Action Localization

Replay: Multi-modal Multi-view Acted Videos for Casual Holography

1 code implementation • ICCV 2023 • Roman Shapovalov, Yanir Kleiman, Ignacio Rocco, David Novotny, Andrea Vedaldi, Changan Chen, Filippos Kokkinos, Ben Graham, Natalia Neverova

We introduce Replay, a collection of multi-view, multi-modal videos of humans interacting socially.

3D Reconstruction Novel View Synthesis

Efficient batchwise dropout training using submatrices

no code implementations • 9 Feb 2015 • Ben Graham, Jeremy Reizenstein, Leigh Robinson

Dropout networks are generally trained by minibatch gradient descent with a dropout mask turning off some of the units---a different pattern of dropout is applied to every sample in the minibatch.

PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments

no code implementations • NeurIPS 2019 • Ben Graham, David Novotny, Jeremy Reizenstein

Given a set of a reference RGBD views of an indoor environment, and a new viewpoint, our goal is to predict the view from that location.