A training-free decoding method that splits images into complementary SAM-based parts and adaptively contrasts token distributions to reduce hallucinations in vision-language models.
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
A training-free decoding method that splits images into complementary SAM-based parts and adaptively contrasts token distributions to reduce hallucinations in vision-language models.