Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness.
Fanny YangZuowen WangChristina Heinze-DemlPublished in: NeurIPS (2019)
Keyphrases
- worst case
- image transformations
- high accuracy
- computational complexity
- computational efficiency
- computational cost
- spatio temporal
- classification accuracy
- upper bound
- prediction accuracy
- temporal resolution
- average case
- spatial and temporal
- spatial information
- spatial data
- geographic information systems
- spatial relationships
- highly accurate
- spatial distribution
- np hard
- lower bound
- neural network