.png){kind=icon}
.png){kind=icon}
Return
Derm-Align: Dermatological diagnosis through multi-modal alignment and prompt learning
.png){kind=icon}
PRE
AI
J
J
C
L
G
DOI：10.1016/j.bspc.2026.111204.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Propose an efficient framework for rapid development of skin disease classification models. • Propose a novel dual adaptation strategy combining vision-language joint fine-tuning with prompt learning. • Design an automated modality completion pipeline for generate image-text pairs of skin disease images. • Present extensive experiments for performance evaluation on skin disease classification. • Publish a new dermatological dataset.
Journal
IF:
4.9
Papers:
9.7K
Citations:
2.4W
Organization
Cited Papers