Jump to content

Convolutional neural network: Difference between revisions

Line 156: Line 156:
==Spherical Images==
==Spherical Images==
There are many ways to adapt convolutional layers to spherical images.
There are many ways to adapt convolutional layers to spherical images.
Below are just a few that I've seen.


* [http://papers.nips.cc/paper/6656-learning-spherical-convolution-for-fast-features-from-360-imagery Learning Spherical Convolution for Fast Features from 360 Imagery (NIPS 2017)] proposes using different kernels with different weights and sizes for different altitudes \(\phi\).
* [http://papers.nips.cc/paper/6656-learning-spherical-convolution-for-fast-features-from-360-imagery Learning Spherical Convolution for Fast Features from 360 Imagery (NIPS 2017)] proposes using different kernels with different weights and sizes for different altitudes \(\phi\).