Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question Answering
In grounded remote sensing visual question answering, a model produces a textual answer and identifies relevant objects in the image as grounding evidence.
ProofPaper ↗
Key points
- Existing evaluations measure answer correctness and localization quality, but do not directly assess answer-grounding consistency.
- We propose the Answer-Evidence Support Protocol (AESP) to assess this consistency through evidence support: whether the grounding evidence supports the model's own answer.
- We further construct the Grounded Remote Sensing Visual Question Answering (G-RSVQA) benchmark, containing 15,027 samples with questions, reference answers, and all related object-level annotations.
- Experiments on seven grounded vision--language models reveal failures of evidence support across all three question types.
Sources (1)
- [1]Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question AnsweringarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 02:15 PM
In grounded remote sensing visual question answering, a model produces a textual answer and identifies relevant objects in the image as grounding evidence.
Existing evaluations measure answer correctness and localization quality, but do not directly assess answer-grounding consistency.
Extractive summary: sentences quoted from the sources.