COCO-OOC goes beyond standard object detection to ask the question: Which objects are out-of-context (OOC)? Given an image with a set of objects, the goal of COCO-OOC is to determine if an object is inconsistent with the contextual relations, where it must detect the OOC object with a bounding box.
COCO-OOC is derived from COCO by inserting objects into images that violate contextual relationships compared to the existing objects in a scene.
COCO-OOC has 106,036 images with two kinds of OOC violations: co-occurrence and size.
Variants: COCO-OOC
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Anomaly Detection | GCRN | Detecting out-of-context objects using contextual … | 2022-02-11 |
Recent papers with results on this dataset: