AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Gauge Equivariant Transformer

Lingshen He, Yiming Dong, Yisen Wang, Dacheng Tao, Zhouchen Lin

NeurIPS 2021 · Architectures and efficiency › Attention and transformers · approach: Attention head and block redesign · 6 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
use GET instead of HSNGET · SHREC shape classificationaccuracy (%): 96.1 -> 99.2Improved
use GET instead of MeshCNNGET · Human Body Segmentationaccuracy (%): 92.3 -> 92.6Improved
GET has 1/7 the parameters of HSNGET · SHREC shape classificationparameters: 78K -> 11KImproved
GET has 1/15 the parameters of MeshCNNGET · Human Body Segmentationparameters: 2.28M -> 148KImproved
increase group order N from 3 to 9 (ablation)GET · Human Body Segmentationaccuracy (%): 91.2 -> 92.6Improved
increase N from 9 to 11 (ablation)GET · Human Body Segmentationaccuracy (%): 92.6 -> 92.5No clear effect
replace gauge-equivariant model with non-equivariant GAT (ablation)GET · Human Body Segmentationaccuracy (%): 92.6 -> 81.1Hurt
replace attention with convolution (ablation)GET · Human Body Segmentationaccuracy (%): 92.6 -> 92.3Hurt
no rotation data augmentationGET · SHREC shape classificationaccuracy (%)Improved

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