MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models.
Yongzhu MiaoShasha LiJintao TangTing WangPublished in: CoRR (2023)
Keyphrases
- multi modal
- language model
- pre trained
- language modeling
- training data
- n gram
- probabilistic model
- computer vision
- training examples
- information retrieval
- query expansion
- speech recognition
- audio visual
- control signals
- retrieval model
- high dimensional
- test collection
- language models for information retrieval
- relevance model
- data sets
- active learning
- low level
- deformable models
- decision trees
- learning algorithm
- training set
- medical images