TL;DR
A theoretical analysis framework for multiple-source domain adaptation based on covering numbers in statistical learning theory is provided and an adversarial multiple feature spaces adaptation network (AMFSAN) is proposed for MDA according to the theoretical results.
PAPT++ is introduced, a risk-aware adversarial generation-training framework for SDG that progressively exposes the classifier to challenging yet semantically consistent variations.
This work proposes MeanFlow-Transfer, which maps heterogeneous source outputs into a shared velocity representation, uses it to initialize an MF generator from the source weights, and optimizes an MF objective on the target domain, and introduces Continuous Adversarial MeanFlow, a post-training stage that extends conti...
An upper bound of the generalization error for universal domain adaptation is provided and a novel UniDA algorithm called Joint Distribution Alignment for Universal Domain Adaptation (JAUA), which aligns the joint distributions by minimizing the distribution discrepancy calculated by Chi-Square divergence is proposed.
Results support the effectiveness of the proposed dual-branch self-guided network (DBSGN) in the studied single-source domain-generalization setting.
In recent years, unsupervised transfer learning based on deep domain adaptation techniques has successfully solved the domain shift problem in machinery fault diagnosis, with a basic assumption that target and source domains share the same label space. However, the label space of the target domain is usually a subset o...
Experimental results show that TransPileSiam consistently improves downstream recognition under limited-label conditions and improves robustness, label efficiency, and cross-domain generalization for practical SEI tasks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
