# Unsupervised Domain Adaptation via Discriminative Manifold Propagation

arXiv: https://arxiv.org/abs/2008.10030 · HTML: https://mlsanity.com/paper/2008.10030/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2020.

## Built on by (most cited first, 30 of 33)

- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain](https://mlsanity.com/paper/2202.10725/) (2022)
- [Conditional Bures Metric for Domain Adaptation](https://mlsanity.com/paper/2108.00302/) (2021)
- [Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation](https://mlsanity.com/paper/2109.03478/) (2021)
- [Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.02089/) (2021)
- [Slimmable Domain Adaptation](https://mlsanity.com/paper/2206.06620/) (2022)
- [Towards Unsupervised Domain Adaptation via Domain-Transformer](https://mlsanity.com/paper/2202.13777/) (2022)
- [COD: Learning Conditional Invariant Representation for Domain Adaptation Regression](https://mlsanity.com/paper/2408.06638/) (2024)
- [Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning](https://mlsanity.com/paper/2103.02808/) (2021)
- [Deep Least Squares Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2111.02207/) (2021)
- [Generalized Label Shift Correction via Minimum Uncertainty Principle: Theory and Algorithm](https://mlsanity.com/paper/2202.13043/) (2022)
- [Discriminative Radial Domain Adaptation](https://mlsanity.com/paper/2301.00383/) (2023)
- [Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression](https://mlsanity.com/paper/2401.13721/) (2024)
- [Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning](https://mlsanity.com/paper/2107.01361/) (2021)
- [HierMUD: Hierarchical Multi-task Unsupervised Domain Adaptation between Bridges for Drive-by Damage Diagnosis](https://mlsanity.com/paper/2107.11435/) (2021)
- [SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss](https://mlsanity.com/paper/2202.09515/) (2022)
- [Maximizing Conditional Independence for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2203.03212/) (2022)
- [When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights](https://mlsanity.com/paper/2406.16608/) (2024)
- [Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation](https://mlsanity.com/paper/2407.09524/) (2024)
- [Partial Domain Adaptation via Importance Sampling-based Shift Correction](https://mlsanity.com/paper/2507.20191/) (2025)
- [Consecutive Knowledge Meta-Adaptation Learning for Unsupervised Medical Diagnosis](https://mlsanity.com/paper/2209.10425/) (2022)
- [A Fourier Transform Framework for Domain Adaptation](https://mlsanity.com/paper/2403.07798/) (2024)
- [Inference for Similarity and Alignability between Noisy High-Dimensional Datasets](https://mlsanity.com/paper/2511.21074/) (2025)
- [Foreground Object Structure Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06543/) (2021)
- [Geometry-Aware Unsupervised Domain Adaptation](https://mlsanity.com/paper/2112.11041/) (2021)
- [Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2203.06836/) (2022)
- [Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment](https://mlsanity.com/paper/2305.12649/) (2023)
- [Deep Feature Registration for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.16100/) (2023)
- [Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding](https://mlsanity.com/paper/2312.13633/) (2023)
- [Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach](https://mlsanity.com/paper/2406.14274/) (2024)

## Abstract (arXiv)

Unsupervised domain adaptation is effective in leveraging rich information from a labeled source domain to an unlabeled target domain. Though deep learning and adversarial strategy made a significant breakthrough in the adaptability of features, there are two issues to be further studied. First, hard-assigned pseudo labels on the target domain are arbitrary and error-prone, and direct application of them may destroy the intrinsic data structure. Second, batch-wise training of deep learning limits the characterization of the global structure. In this paper, a Riemannian manifold learning framework is proposed to achieve transferability and discriminability simultaneously. For the first issue, this framework establishes a probabilistic discriminant criterion on the target domain via soft labels. Based on pre-built prototypes, this criterion is extended to a global approximation scheme for the second issue. Manifold metric alignment is adopted to be compatible with the embedding space. The theoretical error bounds of different alignment metrics are derived for constructive guidance. The proposed method can be used to tackle a series of variants of domain adaptation problems, including both vanilla and partial settings. Extensive experiments have been conducted to investigate the method and a comparative study shows the superiority of the discriminative manifold learning framework.