Enhancing the accuracy of prototype learning in road anomaly segmentation by adding adversarial perturbations to data.
Yu-Sian LinChow-Sing LinPublished in: Multim. Tools Appl. (2024)
Keyphrases
- data collection
- data sets
- data analysis
- synthetic data
- learning systems
- prior knowledge
- learning process
- database
- data points
- human experts
- unsupervised learning
- data sources
- raw data
- knowledge discovery
- supervised learning
- data mining techniques
- background knowledge
- training data
- learning algorithm
- original data
- volume data
- input data
- image data
- end users
- reinforcement learning
- high quality