Meta-learning Fine-tuned Feature Extractor for Few-shot Image Classification: A Case Study on Fine-tuning CNN Backbone with Transformer for Few-shot Learning.
Yulin ShenXian ShuaiPublished in: APIT (2022)
Keyphrases
- fine tuning
- fine tuned
- meta learning
- image classification
- learning tasks
- inductive learning
- learning algorithm
- visual features
- domain specific
- machine learning
- machine learning algorithms
- model selection
- prior knowledge
- video sequences
- feature extractor
- supervised learning
- active learning
- image representation
- learning process
- key frames
- feature extraction
- decision trees
- image processing
- data mining