AI Paper Atlas

Research map / Detection and segmentation / CNN features

ArgoTweak: Towards Self-Updating HD Maps through Structured Priors

Lena Wild, Rafael Valencia, Patric Jensfelt

ICCV 2025 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 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
train with ArgoTweak priors instead of rule-based synthetic priorsLaneSegNet prior-aided · ArgoTweak real-world test (training prior comparison, no change modelling)mAP: 76.7 -> 77.7Improved
add any map prior vs no priorLaneSegNet · ArgoTweak real-world test (training prior comparison, no change modelling)mAP: 39.4 -> 77.7Improved
continuous noise priors vs discrete modification priorsLaneSegNet prior-aided · ArgoTweak real-world test (training prior comparison, no change modelling)mAP: 73.5 vs 71.5No clear effect
train on ArgoTweak instead of rule-based priors to reduce sim2real gapChange-aware LaneSegNet · Sim2real gap mACCDelta mACC: -36.0 -> -3.5Improved
add full atomic change annotations vs none (ablation)Change-aware LaneSegNet · ArgoTweak test, annotation granularitymAP: 77.7 -> 78.8Improved
add geometry change annotations to binary change labels (ablation)Binary change head · ArgoTweak test, annotation granularitymAPC: 46.9 -> 44.7Hurt
add geometry change annotations to binary change labels (ablation)Binary change head · ArgoTweak test, annotation granularitymACC: 66.5 -> 70.5Improved
add secondary change heads for marking and geometry (ablation)Full atomic model · ArgoTweak test, annotation granularitymAP: 78.3 -> 78.8Mixed
add secondary heads for marking and geometry (ablation)Full atomic model · ArgoTweak test, annotation granularitymACC: 64.3 -> 64.6No clear effect
cross-attention prior fusion vs prior tokens replacing queriesPrior encoding · ArgoTweakqualitativeImproved

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