Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach. (arXiv:2108.02888v2 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2108.02888

We are concerned with a worst-case scenario in model generalization, in the
sense that a model aims to perform well on many unseen domains while there is
only one single domain available for training. We propose Meta-Learning based
Adversarial Domain Augmentation to solve this Out-of-Domain generalization
problem. The key idea is to leverage adversarial training to create
"fictitious" yet "challenging" populations, from which a model can learn to
generalize with theoretical guarantees. To facilitate fast and desirable domain
augmentation, we …

arxiv cv quantification uncertainty