A lightweight 3D shape classification layer combines a learned latent space projection with spectral convolution in the unit ball, achieving 94.2% on ModelNet10 and 91.8% on ModelNet40 with only three trainable layers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes
A lightweight 3D shape classification layer combines a learned latent space projection with spectral convolution in the unit ball, achieving 94.2% on ModelNet10 and 91.8% on ModelNet40 with only three trainable layers.