AD-Diff Bench
Explore score history ↗Evaluates set-difference captioning on autonomous driving image subsets, with three splits based on annotation filtering, CLIP filtering, and web scraping, yielding natural-language descriptions of differences between target and reference sets.
- Released
- 2026-09-03
- Institutions
- Karlsruhe Institute of Technology · FZI Research Center for Information Technology
- Evaluates
- Autonomous Driving, General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
AD-Diff Bench paper and code
No reported scores are on record for this benchmark yet.