Unsupervised visual domain adaptation via discriminative dictionary evolution

Songsong Wu, Guangwei Gao, Zuoyong Li, Fei Wu, Xiao-Yuan Jing

Abstract: This work focuses on unsupervised visual domain adaptation which is still challenging in visual recognition. Most of the attention has been dedicated to seeking the domain-invariant features of cross-domain data, but they ignores the valuable discriminative information in the source domain. In this paper, we propose a Discriminative Dictionary Evolution (DDE) approach to seek discriminative features robust to domain shift. Specifically, DDE gradually adapts a discriminative dictionary learned from the source domain to the target domain through a dictionary evolving procedure, in which self-selected atoms of the dictionary are updated with $$\ell _{2,1}$$ ℓ 2 , 1 -norm-based regularization. DDE produces domain-invariant representations for cross-domain visual recognition meanwhile promotes the discriminativeness of the dictionary. Empirical results on real-world data sets demonstrate the advantages of the proposed approach over existing competitive methods.