Research map / Detection and segmentation / Open-set and few-shot detection
Structured Output Prediction for Semantic Perception in Autonomous Vehicles
Rein Houthooft, Cedric De Boom, Stijn Verstichel, Femke Ongenae, Filip De Turck
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 second-degree neighbor connectivity to default SSVM (2-table) (ablation) | SSVM · CamVid average | F1: 35.9 -> 39.8 | Improved |
| Add second-degree neighbor connectivity to default SSVM (2-table) (ablation) | SSVM · KITTI average | F1: 59.4 -> 60.7 | Improved |
| Add structured prediction (pairwise potentials) over independent logistic regression (ablation) | SSVM default · CamVid average | F1: 25.8 -> 35.9 | Improved |
| Add structured prediction over independent logistic regression (ablation) | SSVM default · KITTI average | F1: 49.5 -> 59.4 | Improved |
| Add second-degree neighbors to SSVM (ablation) | SSVM · CamVid class bridge | F1: 00 -> 62 | Improved |
| Add second-degree neighbors to SSVM (ablation) | SSVM · CamVid class animal | F1: 17 -> 25 | Improved |
| Add second-degree neighbors to SSVM (ablation) | SSVM · KITTI class fence | F1: 35 -> 40 | Improved |
| Add second-degree neighbors to SSVM (ablation) | SSVM · CamVid class building | F1: 83 -> 81 | No clear effect |
| Add structured prediction over logistic regression (ablation) | SSVM default · CamVid class pole | F1: 10 -> 07 | Hurt |
| Add structured prediction over logistic regression (ablation) | SSVM default · KITTI class pole | F1: 10 -> 01 | Hurt |
| Add structured prediction over logistic regression (ablation) | SSVM default · CamVid class pedestrian | F1: 23 -> 15 | Hurt |
| Add structured prediction over logistic regression (ablation) | SSVM default · CamVid class misc. text | F1: 09 -> 00 | Hurt |
Closest papers by meaning
- Structural Information Guided Multimodal Pre-training for Vehicle-Centric Perception (AAAI 2024 · similarity 0.87)
- Weakly Supervised Semantic Segmentation for Driving Scenes (AAAI 2024 · similarity 0.87)
- RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding (CVPR 2026 · similarity 0.86)
- In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images (CVPR 2019 · similarity 0.86)
- R$$^{2}$$S100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild (IJCV 2024 · similarity 0.86)
- VLM2Scene: Self-Supervised Image-Text-LiDAR Learning with Foundation Models for Autonomous Driving Scene Understanding (AAAI 2024 · similarity 0.85)
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.
