Submanifold Sparse Convolutional Networks

06/05/2017
by   Benjamin Graham, et al.
0

Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc. Whilst some of this data is naturally dense (for instance, photos), many other data sources are inherently sparse. Examples include pen-strokes forming on a piece of paper, or (colored) 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard "dense" implementations of convolutional networks are very inefficient when applied on such sparse data. We introduce a sparse convolutional operation tailored to processing sparse data that differs from prior work on sparse convolutional networks in that it operates strictly on submanifolds, rather than "dilating" the observation with every layer in the network. Our empirical analysis of the resulting submanifold sparse convolutional networks shows that they perform on par with state-of-the-art methods whilst requiring substantially less computation.

READ FULL TEXT
research
11/28/2017

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Convolutional networks are the de-facto standard for analyzing spatio-te...
research
01/08/2020

Convolutional Networks with Dense Connectivity

Recent work has shown that convolutional networks can be substantially d...
research
08/25/2016

Densely Connected Convolutional Networks

Recent work has shown that convolutional networks can be substantially d...
research
07/06/2018

Tangent Convolutions for Dense Prediction in 3D

We present an approach to semantic scene analysis using deep convolution...
research
03/27/2023

Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis

In this paper, we propose binary sparse convolutional networks called BS...
research
09/29/2020

Lip-reading with Densely Connected Temporal Convolutional Networks

In this work, we present the Densely Connected Temporal Convolutional Ne...
research
01/08/2019

Stable Electromyographic Sequence Prediction During Movement Transitions using Temporal Convolutional Networks

Transient muscle movements influence the temporal structure of myoelectr...

Please sign up or login with your details

Forgot password? Click here to reset