6DCNN with roto-translational convolution filters for volumetric data processing
This addresses protein structure prediction, a domain-specific problem, with incremental improvements in performance.
The paper tackles the problem of detecting relative positions and orientations of local patterns in 3D volumetric data by introducing 6DCNN, which improves over baselines and outperforms state-of-the-art on CASP protein structure prediction datasets.
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.