Research map / Detection and segmentation / Open-set and few-shot detection
SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Pascal Fua, Mathieu Salzmann, Matthias Rottmann
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 |
|---|---|---|---|
| Use a generative-model method rather than the classification-derived baselines | Anomaly and obstacle segmentation · RoadAnomaly21 and RoadObstacle21 | AuPRC | Improved |
| Use maximized softmax entropy rather than image resynthesis | Anomaly segmentation · RoadAnomaly21 test | AuPRC: 52.3 -> 85.5 | Improved |
| Use maximized softmax entropy rather than SynBoost | Obstacle segmentation · RoadObstacle21 test | AuPRC: 70.3 -> 85.1 | Improved |
| Use anomaly/obstacle proxy data to train the detector | Anomaly and obstacle segmentation · RoadAnomaly21 and RoadObstacle21 | AuPRC | Improved |
| Apply feature-statistics methods under domain shift | Mahalanobis and embedding density · RoadObstacle21 | AuPRC | Hurt |
| Use component-wise evaluation in addition to pixel-wise evaluation | Anomaly segmentation evaluation · RoadAnomaly21 and RoadObstacle21 | component-wise average F1 | Mixed |
| Use camera-only anomaly methods on the LiDAR-guided small-obstacle dataset | Evaluated anomaly segmentation methods · LiDAR guided Small Obstacle dataset | performance | Hurt |
Closest papers by meaning
- A Dataset for Semantic Segmentation in the Presence of Unknowns (CVPR 2025 · similarity 0.92)
- Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving (CVPR 2025 · similarity 0.90)
- Weakly Supervised Semantic Segmentation for Driving Scenes (AAAI 2024 · similarity 0.87)
- Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenes (AAAI 2024 · similarity 0.87)
- Open-World Semantic Segmentation Including Class Similarity (CVPR 2024 · similarity 0.87)
- MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning (NeurIPS 2024 · similarity 0.86)
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.
