Research map / Detection and segmentation / Open-set and few-shot detection
Road Anomaly Detection by Partial Image Reconstruction With Segmentation Coupling
Tomas Vojir, Tomáš Šipka, Rahaf Aljundi, Nikolay Chumerin, Daniel Olmeda Reino, Jiri Matas
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 the SSIM reconstruction module to the segmentation network (ablation) | JSR-Net · Average over 4 datasets | AP (%): 31.9 -> 78.9 | Improved |
| add trained segmentation coupling to the untrained product (ablation) | JSR-Net · Average over 4 datasets | AP (%): 78.9 -> 79.1 | No clear effect |
| add auxiliary SSIM reconstruction loss L_R (ablation) | JSR-Net · Average over 4 datasets | AP (%): 79.1 -> 82.9 | Improved |
| use SSIM instead of L2 as reconstruction error (ablation) | JSR-Net · Average over 4 datasets | AP (%): 69.5 -> 82.9 | Improved |
| add synthetic anomaly polygon augmentation (ablation) | JSR-Net · Average over 4 datasets | AP (%): 60.9 -> 82.9 | Improved |
| use SSIM instead of L2 reconstruction error (ablation) | JSR-Net · Average over 4 datasets | FPR95 (%): 10.2 -> 5.1 | Improved |
| add the synthetic augmentation (ablation) | JSR-Net · Average over 4 datasets | FPR95 (%): 11.5 -> 5.1 | Improved |
| switch backbone from Mobilenet v2 to ResNet-101 checkp1 (ablation) | JSR-Net · Average over 4 datasets | AP (%): 78.7 -> 82.9 | Improved |
| switch backbone from Xception to ResNet-101 checkp1 (ablation) | JSR-Net · Average over 4 datasets | AP (%): 82.1 -> 82.9 | No clear effect |
| use stronger segmentation checkpoint (51.6 -> 66.1 mIoU) (ablation) | JSR-Net ResNet-101 · Average over 4 datasets | AP (%): 82.9 -> 83.7 | No clear effect |
| replace Resynthesis-PSPNet with JSR-Net checkp2 | Road Anomaly detection · Road Anomaly | AP (%): 76.4 -> 94.4 | Improved |
| replace Resynthesis-PSPNet with JSR-Net checkp1 | Road anomaly detection · Lost and Found | FPR95 (%): 43.1 -> 3.6 | Improved |
Closest papers by meaning
- SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation (NeurIPS 2021 · similarity 0.90)
- Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving (CVPR 2025 · similarity 0.89)
- Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenes (AAAI 2024 · similarity 0.87)
- A Dataset for Semantic Segmentation in the Presence of Unknowns (CVPR 2025 · similarity 0.87)
- SDAC: A Multimodal Synthetic Dataset for Anomaly and Corner Case Detection in Autonomous Driving (AAAI 2024 · similarity 0.84)
- Open-World Semantic Segmentation Including Class Similarity (CVPR 2024 · similarity 0.84)
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.
