DualFairVL jointly debiases CLIP's text and image branches via text-guided prompts, cross-attention, a hypernetwork, and prototype losses, reporting state-of-the-art AUC and fairness (DEOdds, DPD) on eight medical imaging datasets in in-distribution and out-of-distribution settings.
In: ICLR (2023)
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
-
Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models
DualFairVL jointly debiases CLIP's text and image branches via text-guided prompts, cross-attention, a hypernetwork, and prototype losses, reporting state-of-the-art AUC and fairness (DEOdds, DPD) on eight medical imaging datasets in in-distribution and out-of-distribution settings.