ContextShift Benchmark
Explore score history ↗ContextShift is a controlled benchmark that manipulates object-context relationships in COCO images to isolate context as an independent variable for object detection evaluation.
- Released
- 2026-06-08
- Institutions
- Ben-Gurion University of the Negev
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ContextShift paper
No reported scores are on record for this benchmark yet.