A prompt-driven diffusion augmentation pipeline with a custom weighted loss gives modest PAR improvements, but test-set tuning inflates the reported gains.
Diffusion models in vision: A sur- vey,
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
-
A Data-Centric Approach to Pedestrian Attribute Recognition: Synthetic Augmentation via Prompt-driven Diffusion Models
A prompt-driven diffusion augmentation pipeline with a custom weighted loss gives modest PAR improvements, but test-set tuning inflates the reported gains.