Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains
We show a hardness result for the number of training domains required to achieve a small
population error in the test domain. Although many domain generalization algorithms have …
population error in the test domain. Although many domain generalization algorithms have …
Understanding and improving robustness and uncertainty estimation in deep learning
D Stutz - 2022 - publikationen.sulb.uni-saarland.de
Deep learning is becoming increasingly relevant for many high-stakes applications such as
autonomous driving or medical diagnosis where wrong decisions can have massive impact …
autonomous driving or medical diagnosis where wrong decisions can have massive impact …