1. Averaging weights leads to wider optima and better generalization;izmailov;34th Conference on Uncertainty in Artificial Intelligence 2018 UAI 2018,0
2. Test-time training with self-supervision for generalization under distribution shifts;sun;International Conference on Machine Learning,0
3. Cycada: Cycle-consistent adversarial domain adaptation;hoffman;International Conference on Machine Learning,0
4. Improving robustness against common corruptions by covariate shift adaptation;schneider;Advances in neural information processing systems,2020
5. Overcoming catastrophic forgetting in neural networks;kirkpatrick;Proceedings of the National Academy of Sciences,0