A multi-level feature fusion approach using query-based cross-attention slightly improves AIGC image quality and text-image correspondence scores on three benchmarks, but the gains are marginal and not always the best.
Hierarchical text-con ditional image generation with clip latents,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Hierarchical Fusion and Joint Aggregation: A Multi-Level Feature Representation Method for AIGC Image Quality Assessment
A multi-level feature fusion approach using query-based cross-attention slightly improves AIGC image quality and text-image correspondence scores on three benchmarks, but the gains are marginal and not always the best.