arXiv Open Access 2020

Voronoi Convolutional Neural Networks

Soroosh Yazdani Andrea Tagliasacchi

Lihat Sumber

Abstrak

In this technical report, we investigate extending convolutional neural networks to the setting where functions are not sampled in a grid pattern. We show that by treating the samples as the average of a function within a cell, we can find a natural equivalent of most layers used in CNN. We also present an algorithm for running inference for these models exactly using standard convex geometry algorithms.

Topik & Kata Kunci

cs.CV

Penulis (2)

Soroosh Yazdani

Andrea Tagliasacchi

Format Sitasi

APA MLA BibTeX

Yazdani, S., Tagliasacchi, A. (2020). Voronoi Convolutional Neural Networks. https://arxiv.org/abs/2010.11339

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓