AI Paper Atlas

Research map / Graph learning / GNN architectures

TD-Road: Top-Down Road Network Extraction with Holistic Graph Construction

Yang He, Ravi Garg, Amber Roy Chowdhury

ECCV 2022 · Graph learning › GNN architectures · approach: Graph structure learning · 23 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 neighbor-enhanced context to relation reasoning (ablation)TD-Road · City-ScaleAPLS: 62.17 -> 65.74Improved
add neighbor-enhanced context to relation reasoning (ablation)TD-Road · SpaceNetAPLS: 60.91 -> 65.15Improved
add neighbor-enhanced context to relation reasoning (ablation)TD-Road · City-ScaleTOPO F1: 72.83 -> 76.43Improved
add neighbor-enhanced context to relation reasoning (ablation)TD-Road · SpaceNetTOPO F1: 77.74 -> 81.15Improved
use road-mask weighted BCE instead of plain BCE (ablation)TD-Road (naive) · City-Scale (naive relation module)APLS: 60.32 -> 62.17Improved
use road-mask weighted BCE instead of plain BCE (ablation)TD-Road (naive) · City-Scale (naive relation module)TOPO F1: 60.32 -> 62.17Improved
use road-mask weighted BCE instead of focal loss (ablation)TD-Road (naive) · City-Scale (naive relation module)APLS: 47.95 -> 62.17Improved
use focal loss instead of plain BCE (ablation)TD-Road (naive) · City-Scale (naive relation module)precision: 75.71 -> 80.82Mixed
vary connectedness threshold 0.3 to 0.5 (ablation)TD-Road · City-ScaleAPLSNo clear effect
vary key point threshold 0.3 to 0.5 (ablation)TD-Road · City-ScaleAPLSHurt
replace ResNet-34 with DLA backbone (Sat2Graph) versus oursSat2Graph vs TD-Road · City-ScaleAPLS: 63.14 vs 65.74Mixed

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