AI Paper Atlas

Research map / Detection and segmentation / CNN features

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Subeesh Vasu, Mateusz Kozinski, Leonardo Citraro, and Pascal Fua

ECCV 2020 · Detection and segmentation › CNN features · approach: Lane detection · 11 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 TopoAL spatially-aware dynamic-label discriminator (ablation)UNet · RoadTracerTLTS correct: 0.323 -> 0.388Improved
add TopoAL spatially-aware dynamic-label discriminator (ablation)UNet · RoadTracerAPLS: 0.619 -> 0.666Improved
add TopoAL spatially-aware dynamic-label discriminator (ablation)UNet · RoadTracerCCQ quality: 0.632 -> 0.658Improved
add TopoAL spatially-aware dynamic-label discriminator (ablation)DRU · RoadTracerTLTS correct: 0.437 -> 0.480Improved
add TopoAL spatially-aware dynamic-label discriminator (ablation)DRU · RoadTracerAPLS: 0.697 -> 0.725Improved
add TopoAL spatially-aware dynamic-label discriminator (ablation)DRU · RoadTracerCCQ quality: 0.656 -> 0.657No clear effect
add TopoAL spatially-aware dynamic-label discriminator (ablation)DRU · RoadTracerH&M F1: 0.768 -> 0.787Improved
use standard single-label GAN discriminator instead of no GAN (ablation)UNet · RoadTracerTLTS correct: 0.323 -> 0.328No clear effect
use standard single-label GAN discriminator instead of no GAN (ablation)UNet · RoadTracerAPLS: 0.619 -> 0.607Hurt
use standard single-label GAN discriminator instead of no GAN (ablation)UNet · RoadTracerJUNCT F1: 0.792 -> 0.776Hurt
use TopoAL discriminator instead of single-label GAN discriminator (ablation)UNet · RoadTracerTLTS correct: 0.328 -> 0.388Improved

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