VLMs caption real objects effectively but degrade on 3D-printed fakes in robotic scenes, while some standard metrics fail to detect the factual errors from this domain shift.
In: Computer Vision–ECCV 2016: 14th European Con- ference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V 14 (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding
VLMs caption real objects effectively but degrade on 3D-printed fakes in robotic scenes, while some standard metrics fail to detect the factual errors from this domain shift.