6DCNN with Roto-Translational Convolution Filters for Volumetric Data Processing

Authors

  • Dmitrii Zhemchuzhnikov Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK
  • Ilia Igashov Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK
  • Sergei Grudinin Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK

DOI:

https://doi.org/10.1609/aaai.v36i4.20396

Keywords:

Domain(s) Of Application (APP)

Abstract

In this work, we introduce 6D Convolutional Neural Network (6DCNN) designed to tackle the problem of detecting relative positions and orientations of local patterns when processing three-dimensional volumetric data. 6DCNN also includes SE(3)-equivariant message-passing and nonlinear activation operations constructed in the Fourier space. Working in the Fourier space allows significantly reducing the computational complexity of our operations. We demonstrate the properties of the 6D convolution and its efficiency in the recognition of spatial patterns. We also assess the 6DCNN model on several datasets from the recent CASP protein structure prediction challenges. Here, 6DCNN improves over the baseline architecture and also outperforms the state of the art.

Downloads

Published

2022-06-28

How to Cite

Zhemchuzhnikov, D., Igashov, I., & Grudinin, S. (2022). 6DCNN with Roto-Translational Convolution Filters for Volumetric Data Processing. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4707-4715. https://doi.org/10.1609/aaai.v36i4.20396

Issue

Section

AAAI Technical Track on Domain(s) Of Application