AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Gaussian Mixture Convolution Networks

Adam Celarek, Pedro Hermosilla, Bernhard Kerbl, Timo Ropinski, Michael Wimmer

ICLR 2022 · Architectures and efficiency › CNN design · approach: Large and dynamic kernel design · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Represent inputs and convolution kernels as Gaussian mixtures and use analytical convolutionGMCN · MNIST testaccuracy: 99.2\,\% -> 99.4\,\%Improved
Represent 3D inputs as Gaussian mixtures and use GMCN3D classification · ModelNet10 testaccuracy: 92.2\% -> 93.3\%Mixed
Increase depth from 1 to 5 convolution layers (ablation)GMCN · ModelNet10accuracy: 72.5\,\% -> 92.6\,\%Improved
Increase depth from 5 to 6 convolution layers (ablation)GMCN · ModelNet10accuracy: 92.6\,\% -> 92.3\,\%Hurt
Use TreeHEM (T=2) instead of modified EM for reduction fitting (ablation)GMCN · ModelNet10, 64 input Gaussiansaccuracy: 92.2\,\% -> 92.0\,\%Hurt
Use TreeHEM (T=2) instead of TreeHEM (T=4) (ablation)GMCN · ModelNet10, 128 input Gaussiansaccuracy: 92.9\,\% -> 93.4\,\%Improved
Use TreeHEM reduction rather than modified EM (ablation)GMCN · Convolution fitting, layers 1–3RMSE: 0.45 -> 0.36; 0.50 -> 0.21; 0.36 -> 0.22Improved
Fit input GMs with k-means initialization and one EM step rather than k-means+EM (ablation)GMCN · ModelNet10accuracy: 92.1\,\% -> 93.3\,\%Improved
Fit input GMs with random initialization and multiple EM steps rather than k-means (ablation)GMCN · ModelNet10accuracy: 93.3\,\% -> 92.8\,\%Hurt
Fit input GMs with Eckart rather than k-means (ablation)GMCN · ModelNet10accuracy: 93.3\,\% -> 91.0\,\%Hurt
Reduce input representation from 128 to 32 Gaussians without changing internal fitting (ablation)GMCN · ModelNet10accuracy: 92.78 -> 91.44Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy