HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale.
Junying ChenRuyi OuyangAnningzhe GaoShunian ChenGuiming Hardy ChenXidong WangRuifei ZhangZhenyang CaiKe JiGuangjun YuXiang WanBenyou WangPublished in: CoRR (2024)
Keyphrases
- knowledge discovery
- knowledge acquisition
- visual perception
- visual representations
- prior knowledge
- medical knowledge
- knowledge representation
- learning systems
- domain knowledge
- knowledge management
- scale space
- real time
- visual features
- diagnostic systems
- medical diagnosis
- knowledge sources
- domain experts
- knowledge base
- computer vision
- background knowledge
- visual information
- higher level
- data mining techniques
- low level
- visual processing
- multimodal interaction