StreetHazards is a synthetic dataset for anomaly detection, created by inserting a diverse array of foreign objects into driving scenes and re-render the scenes with these novel objects.
Source: Scaling Out-of-Distribution Detection for Real-World Settings
Variants: StreetHazards
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Scene Segmentation | Mask2Anomaly | Unmasking Anomalies in Road-Scene Segmentation | 2023-07-25 |
| Scene Segmentation | LDN121-RPL | Residual Pattern Learning for Pixel-wise … | 2022-11-26 |
| Scene Segmentation | LDN121-DenseHybrid | DenseHybrid: Hybrid Anomaly Detection for … | 2022-07-06 |
Recent papers with results on this dataset: