AI Paper Atlas

Research map / 3D vision / Face and shape

Representation Learning on Unit Ball with 3D Roto-translational Equivariance

Sameera Ramasinghe, Salman Hameed Khan, Nick M. Barnes, Stephen Jay Gould

IJCV 2019 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 9 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
add more convolution layers (2 or 3) (ablation)volumetric conv net · ModelNet10accuracy: 93.8% -> 92.0% and 89.8%Hurt
use volumetric convolution instead of spherical convolution (ablation)FA · ModelNet10accuracy: 76.2% -> 93.8%Improved
add adaptive frequency pooling instead of mean pooling (ablation)FA · ModelNet10accuracy: 84.2% -> 93.8%Improved
add adaptive frequency pooling instead of max pooling (ablation)FA · ModelNet10accuracy: 86.7% -> 93.8%Improved
add adaptive frequency pooling instead of feature concatenation (ablation)FA · ModelNet10accuracy: 87.8% -> 93.8%Improved
add adaptive frequency pooling instead of MIL attention pooling (ablation)FA · ModelNet10accuracy: 90.3% -> 93.8%Improved
add adaptive frequency pooling instead of MIL gated attention pooling (ablation)FA · ModelNet10accuracy: 89.8% -> 93.8%Improved
use angular weighted-softmax loss instead of softmax (ablation)FA · ModelNet10accuracy: 93.8% -> 92.8%Hurt
use generalized angular softmax loss instead of softmax (ablation)FA · ModelNet10accuracy: 93.8% -> 90.7%Hurt
use cosine similarity instead of Euclidean distance for retrieval (ablation)FA · SHREC'17mAP: 0.386 -> 0.452Improved
use cosine similarity instead of KL divergence for retrieval (ablation)FA · SHREC'17mAP: 0.320 -> 0.452Improved
use cosine similarity instead of Bhattacharyya distance for retrieval (ablation)FA · SHREC'17mAP: 0.354 -> 0.452Improved

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