AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Regularized Primitive Graph Learning for Unified Vector Mapping

Lei Wang, Min Dai, Jianan He, Jingwei Huang

ICCV 2023 · Graph learning › Graph self-supervised learning · approach: Multi-view graph clustering · 10 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 shape regularization loss Lreg (ablation)GraphMapper (building) · CrowdAIC-IoU: 82.7 -> 89.5Improved
add direction regression loss Ldir (ablation)GraphMapper (building) · CrowdAIMTA: 33.1° -> 30.4°Improved
add auxiliary loss Laux (ablation)GraphMapper (building) · CrowdAIC-IoU: 89.0 -> 89.5Improved
use incremental (sequential) refinement then relationship reconstruction instead of parallel (ablation)GraphMapper (building) · CrowdAIC-IoU: 78.3 -> 89.5Improved
use incremental reconstruction (ablation)GraphMapper (road) · City-ScaleAPLS: 67.6 -> 68.9Improved
sort points in embedding space for connections instead of thresholding probability (ablation)GraphMapper (road) · City-ScaleAPLS: 66.2 -> 68.9Improved
remove Lreg on IoU (ablation)GraphMapper (building) · CrowdAIIoU: 94.4 vs 94.3No clear effect
replace PolyWorld with GraphMapperbuilding mapping · CrowdAIAP: 63.3 -> 72.8Improved
replace Sat2Graph with GraphMapperroad mapping · City-ScaleTOPO F1: 76.3 -> 85.6Improved
add primitive refinement and relationship reconstruction to segmentation mask (ablation)GraphMapper (building) · CrowdAIAP: 63.6 -> 72.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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