Search Results for author: Benjamin Graham

Found 19 papers, 14 papers with code

DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension

no code implementations ICCV 2021 Roman Shapovalov, David Novotny, Benjamin Graham, Patrick Labatut, Andrea Vedaldi

The method learns, in an end-to-end fashion, a soft partition of a given category-specific 3D template mesh into rigid parts together with a monocular reconstruction network that predicts the part motions such that they reproject correctly onto 2D DensePose-like surface annotations of the object.

3D Reconstruction Structure from Motion

Pri3D: Can 3D Priors Help 2D Representation Learning?

1 code implementation ICCV 2021 Ji Hou, Saining Xie, Benjamin Graham, Angela Dai, Matthias Nießner

Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints.

Contrastive Learning Instance Segmentation +3

Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts

1 code implementation CVPR 2021 Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e. g. point clouds) are notoriously hard.

Instance Segmentation Scene Understanding +1

RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty

1 code implementation20 Nov 2020 Benjamin Graham, David Novotny

Using a set of high-quality sparse keypoint matches, we optimize over the per-frame linear combinations of depth planes and camera poses to form a geometrically consistent cloud of keypoints.

Structure from Motion

Training with Quantization Noise for Extreme Model Compression

3 code implementations ICLR 2021 Angela Fan, Pierre Stock, Benjamin Graham, Edouard Grave, Remi Gribonval, Herve Jegou, Armand Joulin

A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator.

Image Generation Model Compression

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

2 code implementations ICCV 2019 David Novotny, Nikhila Ravi, Benjamin Graham, Natalia Neverova, Andrea Vedaldi

We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images.

Structure from Motion

Unsupervised learning with sparse space-and-time autoencoders

1 code implementation26 Nov 2018 Benjamin Graham

We use spatially-sparse two, three and four dimensional convolutional autoencoder networks to model sparse structures in 2D space, 3D space, and 3+1=4 dimensional space-time.

Handwriting Recognition Motion Capture

The iisignature library: efficient calculation of iterated-integral signatures and log signatures

2 code implementations22 Feb 2018 Jeremy Reizenstein, Benjamin Graham

Iterated-integral signatures and log signatures are vectors calculated from a path that characterise its shape.

Data Structures and Algorithms Mathematical Software Rings and Algebras

Submanifold Sparse Convolutional Networks

5 code implementations5 Jun 2017 Benjamin Graham, Laurens van der Maaten

Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.

Ranked #20 on 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric)

3D Part Segmentation

Low-Precision Batch-Normalized Activations

no code implementations27 Feb 2017 Benjamin Graham

Artificial neural networks can be trained with relatively low-precision floating-point and fixed-point arithmetic, using between one and 16 bits.

Quantization

Confusing Deep Convolution Networks by Relabelling

no code implementations23 Oct 2015 Leigh Robinson, Benjamin Graham

Deep convolutional neural networks have become the gold standard for image recognition tasks, demonstrating many current state-of-the-art results and even achieving near-human level performance on some tasks.

Fractional Max-Pooling

6 code implementations18 Dec 2014 Benjamin Graham

However, if you simply alternate convolutional layers with max-pooling layers, performance is limited due to the rapid reduction in spatial size, and the disjoint nature of the pooling regions.

Image Classification

Spatially-sparse convolutional neural networks

3 code implementations22 Sep 2014 Benjamin Graham

Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification.

Handwriting Recognition Image Classification

Sparse arrays of signatures for online character recognition

no code implementations1 Aug 2013 Benjamin Graham

We show that the path signature, used as a set of features for consumption by a convolutional neural network (CNN), improves the accuracy of online character recognition---that is the task of reading characters represented as a collection of paths.

Cannot find the paper you are looking for? You can Submit a new open access paper.