DeepAI AI Chat
Log In Sign Up

Spherical CNNs on Unstructured Grids

by   Chiyu "Max" Jiang, et al.

We present an efficient convolution kernel for Convolutional Neural Networks (CNNs) on unstructured grids using parameterized differential operators while focusing on spherical signals such as panorama images or planetary signals. To this end, we replace conventional convolution kernels with linear combinations of differential operators that are weighted by learnable parameters. Differential operators can be efficiently estimated on unstructured grids using one-ring neighbors, and learnable parameters can be optimized through standard back-propagation. As a result, we obtain extremely efficient neural networks that match or outperform state-of-the-art network architectures in terms of performance but with a significantly lower number of network parameters. We evaluate our algorithm in an extensive series of experiments on a variety of computer vision and climate science tasks, including shape classification, climate pattern segmentation, and omnidirectional image semantic segmentation. Overall, we present (1) a novel CNN approach on unstructured grids using parameterized differential operators for spherical signals, and (2) we show that our unique kernel parameterization allows our model to achieve the same or higher accuracy with significantly fewer network parameters.


page 2

page 8


Spherical Transformer: Adapting Spherical Signal to ConvolutionalNetworks

Convolutional neural networks (CNNs) have been widely used in various vi...

PDO-eS^2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs

Spherical signals exist in many applications, e.g., planetary data, LiDA...

Kernel Transformer Networks for Compact Spherical Convolution

Ideally, 360 imagery could inherit the deep convolutional neural network...

GMLS-Nets: A framework for learning from unstructured data

Data fields sampled on irregularly spaced points arise in many applicati...

GMLS-Nets: Scientific Machine Learning Methods for Unstructured Data

Data fields sampled on irregularly spaced points arise in many applicati...

3D object classification and retrieval with Spherical CNNs

3D object classification and retrieval presents many challenges that are...

Tangent Images for Mitigating Spherical Distortion

In this work, we propose "tangent images," a spherical image representat...