DeepSphere: a graph-based spherical CNN | OpenReview

DeepSphere: a graph-based spherical CNN Sep 25, 2019 Blind Submission readers: everyone Show Bibtex TL;DR: A graph-based spherical CNN that strikes an interesting balance of trade-offs for a wide variety of applications. Abstract: Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the discretized sphere, strikes a controllable balance between these two de

2 mentions: @hillbig@hillbig
Keywords: cnn
Date: 2020/05/22 00:52

Referring Tweets

@hillbig DeepSphereは回転操作に対し同変な球面CNNとして、サンプルされた点の頂点とその点間の枝の重みを指数カーネルで定めたグラフ上でラプラシアンLを定義し、Lを使ったグラフ畳み込み操作を行う。従来手法(Spherical CNN)より計算/メモリコストが数分の1であり精度も高い。t.co/Lh88AATE7x

Related Entries

Read more [1910.05446] On Empirical Comparisons of Optimizers for Deep Learning
0 users, 5 mentions 2019/10/16 00:50
Read more [1911.05722] Momentum Contrast for Unsupervised Visual Representation Learning
0 users, 11 mentions 2019/11/18 23:21
Read more [2004.01177] Tracking Objects as Pointscontact arXivarXiv Twitter
0 users, 6 mentions 2020/04/03 03:51
Read more [2004.08955] ResNeSt: Split-Attention Networksopen searchopen navigation menucontact arXivarXiv Twit...
0 users, 8 mentions 2020/04/22 06:52
Read more [2004.13621] Exploring Self-attention for Image Recognitionopen searchopen navigation menucontact ar...
0 users, 2 mentions 2020/05/25 00:52