SalArt-VQA Benchmark
Explore score history ↗SalArt-VQA is a closed-set visual question answering benchmark for fine-grained salient artifact understanding in AI-generated images. It includes 950 images and 3,681 human-authored multiple-choice questions covering artifact images, matched real references, and paired generated references. Four aligned question types evaluate presence detection, semantic localization, spatial grounding, and evidence-grounded defect identification, with reference splits for calibration and abstention testing.
- Released
- 2026-06-10
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SalArt-VQA paper and dataset
No reported scores are on record for this benchmark yet.