AI Paper Atlas

Research map / Detection and segmentation / CNN features

Template Matching via Densities on the Roto-Translation Group

Erik J. Bekkers, Marco Loog, Bart M. ter Haar Romeny, Remco Duits

TPAMI 2017 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 28 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 SE(2) orientation-score templates instead of R2 image templates (average templates) (ablation)template matching · ONH detection all imagessuccess rate: 97.87% -> 99.08%Improved
train templates by linear regression instead of averaging (SE(2)) (ablation)SE(2) template · ONH detection all imagessuccess rate: 99.08% -> 99.54%Improved
add regularization to linear regression templates (SE(2)) (ablation)linear regression SE(2) template · ONH detection all imagessuccess rate: 94.01% -> 99.54%Improved
add regularization to logistic regression templates (SE(2)) (ablation)logistic regression SE(2) template · ONH detection all imagessuccess rate: 83.14% -> 99.08%Improved
add regularization to linear regression templates (R2) (ablation)linear regression R2 template · ONH detection all imagessuccess rate: 21.48% -> 97.07%Improved
combine R2 and SE(2) templates (ablation)template matching · ONH detection all imagessuccess rate: 99.08% -> 99.83%Improved
use logistic instead of linear regression for individual templates (ablation)SE(2) templates · ONH detection all imagessuccess rate: 99.54% -> 99.08%Hurt
train templates instead of averaging in combinations (ablation)template combination · ONH detection all imagessuccess rate: 99.19% -> 99.83%Improved
train SE(2) templates by linear regression instead of averaging (ablation)SE(2) template · Fovea detectionsuccess rate: 92.1% -> 94.6%Improved
combine R2 and SE(2) templates (ablation)template matching · Fovea detectionsuccess rate: 94.6% -> 99.3%Improved
use logistic instead of linear regression (ablation)SE(2) template · Pupil detectionsuccess rate: 87.2% -> 94.0%Improved
train templates instead of averaging (ablation)template matching · Pupil detectionsuccess rate: 68.2% -> 95.6%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