The paper introduces TextVQA-C and GQA-C, showing that LLaVA 1.5 loses text-question accuracy most under blur and snow and object-question accuracy most under frost and impulse noise, though only one model is tested.
Image difference captioning with pre-training and contrastive learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analysing the Robustness of Vision-Language-Models to Common Corruptions
The paper introduces TextVQA-C and GQA-C, showing that LLaVA 1.5 loses text-question accuracy most under blur and snow and object-question accuracy most under frost and impulse noise, though only one model is tested.