Domain Adaptation via Rebalanced Sub-domain Alignment
This addresses a limitation in domain adaptation for real-world scenarios where class distributions differ, though it appears incremental as it builds on existing UDA methods.
The paper tackles the problem of unsupervised domain adaptation when source and target domains have different class distributions, proposing a novel generalization bound that reweights source classification error by aligning sub-domains, and shows it improves performance in shifted class distribution scenarios compared to state-of-the-art methods.
Unsupervised domain adaptation (UDA) is a technique used to transfer knowledge from a labeled source domain to a different but related unlabeled target domain. While many UDA methods have shown success in the past, they often assume that the source and target domains must have identical class label distributions, which can limit their effectiveness in real-world scenarios. To address this limitation, we propose a novel generalization bound that reweights source classification error by aligning source and target sub-domains. We prove that our proposed generalization bound is at least as strong as existing bounds under realistic assumptions, and we empirically show that it is much stronger on real-world data. We then propose an algorithm to minimize this novel generalization bound. We demonstrate by numerical experiments that this approach improves performance in shifted class distribution scenarios compared to state-of-the-art methods.