ScaleNet: An Unsupervised Representation Learning Method for Limited Information.
Huili HuangM. Mahdi RoozbahaniPublished in: GCPR (2021)
Keyphrases
- prior knowledge
- unsupervised learning
- learning scheme
- prior information
- high accuracy
- reinforcement learning
- topological map
- visual representation
- statistical information
- neural nets
- segmentation method
- learning algorithm
- preprocessing
- significant improvement
- cost function
- domain knowledge
- dynamic programming
- supervised learning
- background knowledge
- multiple representations
- unsupervised manner
- inference process
- spatial information
- computational cost
- action recognition
- segmentation algorithm
- image representation
- probabilistic model
- model selection
- online learning
- edge detection
- information extraction