Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification.
Yaoqin YeJunjie ZhangHongwei ShiPublished in: CoRR (2024)
Keyphrases
- multi label
- language model
- image classification
- pre trained
- multi label classification
- image annotation
- visual features
- n gram
- information retrieval
- speech recognition
- image features
- feature extraction
- image representation
- computer vision
- training data
- bag of words
- control signals
- probabilistic model
- training examples
- visual words
- graph cuts
- text categorization
- data sets
- image processing
- natural language
- multi modal
- data points
- markov random field