Open-source vision-language models with an XGBoost ensemble can assess residential blight from street-view images, but reported performance is inflated by test-set threshold tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit
Open-source vision-language models with an XGBoost ensemble can assess residential blight from street-view images, but reported performance is inflated by test-set threshold tuning.