Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification.
Zuheng KangYayun HeJianzong WangJunqing PengXiaoyang QuJing XiaoPublished in: CoRR (2023)
Keyphrases
- prior knowledge
- expert knowledge
- data sets
- classification models
- data analysis
- experimental data
- raw data
- high level
- domain experts
- empirical data
- probability distribution
- knowledge discovery
- machine learning
- input data
- expert systems
- test data
- conceptual model
- database
- data mining techniques
- special case
- statistical methods
- classification algorithm
- semantically rich
- missing information
- confidence scores
- classification method
- privacy preserving
- training samples
- labeled data
- model selection
- text classification
- image classification
- training set
- data structure
- feature extraction
- knowledge base