Anomaly Instance Segmentation Benchmark
OoDIS is a benchmark dataset for anomaly instance segmentation, crucial for autonomous vehicle safety. It extends existing anomaly segmentation benchmarks to focus on the segmentation of individual out-of-distribution (OOD) objects.
The dataset addresses the need for identifying and segmenting unknown objects, which are critical to avoid accidents. It includes diverse scenes with various anomalies, pushing the boundaries of current segmentation capabilities.
The benchmark is focused on evaluation of detection and instance segmentation of unexpected obstacles on roads.
For more details, refer to the OoDIS paper
Variants: OoDIS
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Object Detection | UGainS | UGainS: Uncertainty Guided Anomaly Instance … | 2023-08-03 |
| Instance Segmentation | UGainS | UGainS: Uncertainty Guided Anomaly Instance … | 2023-08-03 |
| Object Detection | Mask2Anomaly | Unmasking Anomalies in Road-Scene Segmentation | 2023-07-25 |
| Instance Segmentation | Mask2Anomaly | Unmasking Anomalies in Road-Scene Segmentation | 2023-07-25 |
| Object Detection | U3HS | Segmenting Known Objects and Unseen … | 2022-09-12 |
| Instance Segmentation | U3HS | Segmenting Known Objects and Unseen … | 2022-09-12 |
Recent papers with results on this dataset: