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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add TopoAL spatially-aware dynamic-label discriminator (ablation) | UNet · RoadTracer | TLTS correct: 0.323 -> 0.388 | Improved |
| add TopoAL spatially-aware dynamic-label discriminator (ablation) | UNet · RoadTracer | APLS: 0.619 -> 0.666 | Improved |
| add TopoAL spatially-aware dynamic-label discriminator (ablation) | UNet · RoadTracer | CCQ quality: 0.632 -> 0.658 | Improved |
| add TopoAL spatially-aware dynamic-label discriminator (ablation) | DRU · RoadTracer | TLTS correct: 0.437 -> 0.480 | Improved |
| add TopoAL spatially-aware dynamic-label discriminator (ablation) | DRU · RoadTracer | APLS: 0.697 -> 0.725 | Improved |
| add TopoAL spatially-aware dynamic-label discriminator (ablation) | DRU · RoadTracer | CCQ quality: 0.656 -> 0.657 | No clear effect |
| add TopoAL spatially-aware dynamic-label discriminator (ablation) | DRU · RoadTracer | H&M F1: 0.768 -> 0.787 | Improved |
| use standard single-label GAN discriminator instead of no GAN (ablation) | UNet · RoadTracer | TLTS correct: 0.323 -> 0.328 | No clear effect |
| use standard single-label GAN discriminator instead of no GAN (ablation) | UNet · RoadTracer | APLS: 0.619 -> 0.607 | Hurt |
| use standard single-label GAN discriminator instead of no GAN (ablation) | UNet · RoadTracer | JUNCT F1: 0.792 -> 0.776 | Hurt |
| use TopoAL discriminator instead of single-label GAN discriminator (ablation) | UNet · RoadTracer | TLTS correct: 0.328 -> 0.388 | Improved |
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.
- Roadtracer — RoadTracer: Automatic Extraction of Road Networks From Aerial Images (CVPR 2018) · better on 3 of 3 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
- RoadTracer: Automatic Extraction of Road Networks From Aerial Images (CVPR 2018 · similarity 0.91)
- DeepRoadMapper: Extracting Road Topology From Aerial Images (ICCV 2017 · similarity 0.90)
- Improved Road Connectivity by Joint Learning of Orientation and Segmentation (CVPR 2019 · similarity 0.89)
- Joint Segmentation and Path Classification of Curvilinear Structures (TPAMI 2019 · similarity 0.87)
- No More Discrimination: Cross City Adaptation of Road Scene Segmenters (ICCV 2017 · similarity 0.87)
- Patched Line Segment Learning for Vector Road Mapping (AAAI 2024 · similarity 0.87)
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.
