A single-image pipeline generates adversarial 3D pose variations that degrade vision-language model accuracy by up to 80%, and a new benchmark, MM3DTBench, quantifies this vulnerability.
Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
A single-image pipeline generates adversarial 3D pose variations that degrade vision-language model accuracy by up to 80%, and a new benchmark, MM3DTBench, quantifies this vulnerability.