AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

PseudoMapTrainer: Learning Online Mapping without HD Maps

Christian Löwens, Thorben Funke, Jingchao Xie, Alexandru Paul Condurache

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 1 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
lower coverage threshold from 50% to 30% without mask-aware training (ablation)MapTRv2 · Ablation (single-trip pseudo-labels)mean AP: 6.7 -> 5.3Hurt
add rendering and direction losses (ablation)MapTRv2 (tau_m 30%) · Ablation (single-trip pseudo-labels)mean AP: 5.3 -> 6.1Mixed
add PV segmentation loss without projection (ablation)MapTRv2 · Ablation (single-trip pseudo-labels)mean AP: 6.1 -> 6.4Improved
add mask-aware assignment and loss (ablation)MapTRv2 · Ablation (single-trip pseudo-labels)mean AP: 6.4 -> 8.2Improved
add mask-aware assignment and loss (ablation)MapTRv2 · Ablation (single-trip pseudo-labels)road boundary AP: 4.7 -> 8.3Improved
train with multi-trip instead of single-trip pseudo-labelsMapTRv2 + PseudoMapTrainer · nuScenes valmean AP: 8.2 -> 13.2Improved
add PseudoMapTrainer to naive pseudo-label trainingMapTRv2 (multi-trip) · nuScenes valmean AP: 10.5 -> 13.2Improved
use multi-trip pseudo-labels instead of single-trippseudo-label generation · Pseudo-label BEV coveragecoverage ratio: 40.0% -> 65.5%Improved
increase BEV resolution from 5 to 40 pixel/m (ablation)pseudo-label pipeline · Pseudo-label quality, observed arealane divider AP: 3.1 -> 6.5Improved
increase dilation kernel size from 1 to 25 (ablation)pseudo-label pipeline · Pseudo-label quality, observed arealane divider AP: 3.7 -> 6.7Improved
use very small distance step epsilon 1 cm instead of 5 cm (ablation)pseudo-label pipeline · Pseudo-label quality, observed areapedestrian crossing AP: 23.6 -> 20.8Hurt
increase BEV resolution from 5 to 40 pixel/m (ablation)pseudo-label pipeline · Pseudo-label quality, observed areapedestrian crossing AP: 24.0 -> 22.8Hurt

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