HCOENet combines multi-model entity cross-checking with open-set detection to delete hallucinated objects and add descriptions of overlooked traffic objects, with reported F1 gains on a modified POPE evaluation.
Adapt: Action-aware driving caption transformer,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic Scenarios
HCOENet combines multi-model entity cross-checking with open-set detection to delete hallucinated objects and add descriptions of overlooked traffic objects, with reported F1 gains on a modified POPE evaluation.