A multi-aspect contrastive pretraining scheme with LLM-generated disease and concept sub-captions improves zero-shot dermatology classification and retrieval relative to existing vision-language models.
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
-
MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment
A multi-aspect contrastive pretraining scheme with LLM-generated disease and concept sub-captions improves zero-shot dermatology classification and retrieval relative to existing vision-language models.