5,321
edits
Convolutional neural network: Difference between revisions
→Pooling
| Line 109: | Line 109: | ||
During max pooling, remember the indices where you pulled from in "switch variables".<br> | During max pooling, remember the indices where you pulled from in "switch variables".<br> | ||
Then when unpooling, save the max value into those indices. Other indices get values of 0. | Then when unpooling, save the max value into those indices. Other indices get values of 0. | ||
==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 \(\phi\). | |||
* [https://www.tu-chemnitz.de/etit/proaut/publications/schubert19_IV.pdf Circular Convolutional Neural Networks (IV 2019)] proposes padding the left and right sides of each input and feature map using pixels such that the input wraps around. | |||
* [https://arxiv.org/abs/1811.08196 SpherePHD (CVPR 2019)] proposes using faces of an icosahedron as pixels. They propose a kernel which considers the neighboring 9 triangles of each triangle. | |||