# Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach

arXiv: https://arxiv.org/abs/1902.08727 · HTML: https://mlsanity.com/paper/1902.08727/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Feb 2019.

## Built on by (most cited first, 13 of 13)

- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.14888/) (2022)
- [Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach](https://mlsanity.com/paper/2302.12047/) (2023)
- [RoCA: Robust Cross-Domain End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.10145/) (2025)
- [Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.15973/) (2021)
- [Vicinal and categorical domain adaptation](https://mlsanity.com/paper/2103.03460/) (2021)
- [Unsupervised Domain Adaptation Based on the Predictive Uncertainty of Models](https://mlsanity.com/paper/2211.08866/) (2022)
- [Uncertainty-aware self-training with expectation maximization basis transformation](https://mlsanity.com/paper/2405.01175/) (2024)
- [Increasing Model Generalizability for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2209.14644/) (2022)
- [AIDA: Legal Judgment Predictions for Non-Professional Fact Descriptions via Partial-and-Imbalanced Domain Adaptation](https://mlsanity.com/paper/2302.07728/) (2023)
- [Maximizing Information in Domain-Invariant Representation Improves Transfer Learning](https://mlsanity.com/paper/2306.00262/) (2023)
- [Unsupervised Domain Adaptation Using Compact Internal Representations](https://mlsanity.com/paper/2401.07207/) (2024)
- [Decision Boundary Optimization-Informed Domain Adaptation](https://mlsanity.com/paper/2502.06498/) (2025)

## Abstract (arXiv)

In unsupervised domain adaptation, it is widely known that the target domain error can be provably reduced by having a shared input representation that makes the source and target domains indistinguishable from each other. Very recently it has been studied that not just matching the marginal input distributions, but the alignment of output (class) distributions is also critical. The latter can be achieved by minimizing the maximum discrepancy of predictors (classifiers). In this paper, we adopt this principle, but propose a more systematic and effective way to achieve hypothesis consistency via Gaussian processes (GP). The GP allows us to define/induce a hypothesis space of the classifiers from the posterior distribution of the latent random functions, turning the learning into a simple large-margin posterior separation problem, far easier to solve than previous approaches based on adversarial minimax optimization. We formulate a learning objective that effectively pushes the posterior to minimize the maximum discrepancy. This is further shown to be equivalent to maximizing margins and minimizing uncertainty of the class predictions in the target domain, a well-established principle in classical (semi-)supervised learning. Empirical results demonstrate that our approach is comparable or superior to the existing methods on several benchmark domain adaptation datasets.