Blended-target domain adaptation (BTDA), which implicitly mixes multiple sub-target domains into a fine domain, has attracted more attention in recent years.

Adversarial learning has demonstrated good performance in the unsupervised domain adaptation setting, by learning domain-invariant representations. However, recent work has shown limitations of this approach when label distributions differ between the source and target domains. In this paper, we propose a new assumption, \textit{generalized label shift} ($\glsa$), to improve robustness against mismatched label distributions.

Appendix C contains the proof for trade-off theorem discussed in Section 2.4 of our main In (4), Fubini theorem is invoked to swap the integral signs. This bound is novel since it relates loss on input space and data shift on feature space. Lemma 4. Given a source mixture and a target domain, we have the following d Now we are ready to prove the bound which motivate compressed DI representation. The objective function in Eq. (6) can be viewed as training the optimal hypothesis This estimation is unbiased estimation, i.e., To make it more consistent, we discuss under which condition the Hellinger loss is in the family defined in (10). Model We train a hypothesis ˆ f = ˆ h g and minimize the classification loss w.r.t.

The domain-specific representation is optimized through the meta-learning framework to adapt from source domains, targeting a robust generalization on unseen domains. We empirically show that mDSDI provides competitive results with state-of-the-art techniques in DG.