AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Axis-level Symmetry Detection with Group-Equivariant Representation

Wongyun Yu, Ahyun Seo, Minsu Cho

ICCV 2025 · Architectures and efficiency › CNN design · approach: Group symmetry equivariant networks · 2 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 orientational anchors to axis-level reflection detection (ablation)Axis-level detection baseline · DENDI reflectionsAP@5/10/15: 6.2 -> 16.6, 9.3 -> 19.9, 11.2 -> 21.1Improved
add single-kernel reflectional matching (k=0) (ablation)Axis-level detection + orientational anchors · DENDI reflectionsAP@5/10/15: 16.6 -> 17.6, 19.9 -> 20.7, 21.1 -> 21.8Improved
expand reflectional matching to kernels k=0,1 (ablation)Reflectional matching k=0 · DENDI reflectionsAP@5/10/15: 17.6 -> 18.4, 20.7 -> 22.0, 21.8 -> 23.7Improved
expand reflectional matching to kernels k=0,1,2 (ablation)Reflectional matching k=0,1 · DENDI reflectionsAP@5/10/15: 18.4 -> 18.8, 22.0 -> 22.7, 23.7 -> 24.7Improved
add single-kernel rotational matching (k=0) (ablation)Axis-level detection baseline · DENDI rotation centersAP@5/10/15: 31.5 -> 35.9, 34.7 -> 37.8, 35.7 -> 37.0Improved
expand rotational matching to kernels k=0,1 (ablation)Rotational matching k=0 · DENDI rotation centersAP@5/10/15: 35.9 -> 36.2, 37.8 -> 38.2, 37.0 -> 37.4Improved
expand rotational matching to kernels k=0,1,2 (ablation)Rotational matching k=0,1 · DENDI rotation centersAP@5/10/15: 36.2 -> 36.8, 38.2 -> 39.1, 37.4 -> 40.0Improved
full rotational matching (k=0,1,2) on fold classification (ablation)Axis-level detection baseline · DENDI rotation foldfold sAP@5/10/15: 22.5 -> 26.6, 24.6 -> 28.3, 25.3 -> 28.9Improved
use group-equivariant design instead of non-equivariant variant (ablation)Proposed model · DENDI test rotation robustnessRMSE of length map: significantly lower RMSE (no numbers given)Improved
axis-level detection instead of heatmap-based PMCNetOurs vs PMCNet · LDRS reflectionF1: 37.3 -> 43.4Improved
axis-level detection instead of heatmap-based PMCNetOurs vs PMCNet · SDRW reflectionF1: 68.8 -> 68.3No clear effect
axis-level detection instead of EquiSymOurs vs EquiSym · DENDI rotationF1: 22.4 -> 26.8Improved

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