GroundingDINO's high false positive rate make it difficult to detect obj hallucination

[ipheiman]

Hi authors,
Amazing work on post-hoc hallucination mitigation, I am excited to try this out!

I am looking at the individual steps and experimenting with GroundingDINO but found that it has the tendency to give false positives, which is counter-intuitive for flagging out hallucinated objects. This issue is also raised in GroundingDino's repo: IDEA-Research/GroundingDINO#84

I was wondering if you encountered something similar when developing your work. It would be beneficial to hear your opinion on this, thanks!!

[xjtupanda]

Thanks for your attention to our work!

We've met similar issues but haven't figured out a perfect solution for this since this is a problem inherent to the detection model. But most of the time, GroundingDINO worked just fine.

I think this could be a gap where you make improvements. You may try using a VQA model (e.g., BLIP-2) to double-check if something really exists. Or revise the pipeline, like performing a global detection first (like this one recognize-anything) and then checking if the object matches anything in those tags.