A localization-aware VQA metric that probes both correct attribute placement and attribute leakage outperforms current T2I evaluation methods at matching human judgments on a curated fashion dataset.
Title resolution pending
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
-
Evaluating Attribute Confusion in Fashion Text-to-Image Generation
A localization-aware VQA metric that probes both correct attribute placement and attribute leakage outperforms current T2I evaluation methods at matching human judgments on a curated fashion dataset.