Global Variational Inference Enhanced Robust Domain Adaptation
Abstract
Deep learning-based domain adaptation (DA) methods have shown strong performance by learning transferable representations. However, their reliance on mini-batch training limits global distribution modeling, leading to unstable alignment and suboptimal generalization. We propose Global Variational Inference Enhanced Domain Adaptation (GVI-DA), a framework that learns continuous, class-conditional global priors via variational inference to enable structure-aware cross-domain alignment. GVI-DA minimizes domain gaps through latent feature reconstruction, and mitigates posterior collapse using global codebook learning with randomized sampling. It further improves robustness by discarding low-confidence pseudo-labels and generating reliable target-domain samples. Extensive experiments on four benchmarks and thirty-eight DA tasks demonstrate consistent state-of-the-art performance. We also derive the model's evidence lower bound (ELBO) and analyze the effects of prior continuity, codebook size, and pseudo-label noise tolerance. In addition, we compare GVI-DA with diffusion-based generative frameworks in terms of optimization principles and efficiency, highlighting both its theoretical soundness and practical advantages.
Cite
@article{arxiv.2507.03291,
title = {Global Variational Inference Enhanced Robust Domain Adaptation},
author = {Lingkun Luo and Shiqiang Hu and Liming Chen},
journal= {arXiv preprint arXiv:2507.03291},
year = {2025}
}
Comments
The current version has issues in experimental protocol and presentation. Some evaluation settings (Office-Home/ImageCLEF splits & baselines; Secs.4.1 -- 4.2; Tabs.3 -- 5) are not fully aligned with recent practice, and several figures have labeling/flow issues (e.g., Fig.1(e), Figs.2 -- 4). A revised version will follow