Skip to yearly menu bar Skip to main content


A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

Zehao Xiao · Jiayi Shen · Xiantong Zhen · Ling Shao · Cees Snoek

Keywords: [ Bayesian Deep Learning ] [ Adversarial Networks; Theory ] [ Applications -> Computational Biology and Bioinformatics; Applications -> Health; Deep Learning ] [ Algorithms ] [ Model Selection and Structure Learning ]


Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference, by incorporating uncertainty into neural network weights. We couple domain invariance in a probabilistic formula with the variational Bayesian inference. This enables us to explore domain-invariant learning in a principled way. Specifically, we derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network. We empirically demonstrate the effectiveness of our proposal on four widely used cross-domain visual recognition benchmarks. Ablation studies validate the synergistic benefits of our Bayesian treatment when jointly learning domain-invariant representations and classifiers for domain generalization. Further, our method consistently delivers state-of-the-art mean accuracy on all benchmarks.

Chat is not available.