A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

          Zehao Xiao 1 * Jiayi Shen 1 * Xiantong Zhen 1 2 Ling Shao 2 Cees G. M. Snoek 1

              Abstract                Li et al., 2018a) or specific architectures (Li et al., 2017;
   Domain generalization is challenging due to the        D’Innocente & Caputo, 2018). The state-of-the-art relies
   domain shift and the uncertainty caused by the        on advanced deep neural network backbones, known to de-
   inaccessibilit ...