# Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment

arXiv: https://arxiv.org/abs/2002.08675 · HTML: https://mlsanity.com/paper/2002.08675/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 8 of 8)

- [Transferable Semantic Augmentation for Domain Adaptation](https://mlsanity.com/paper/2103.12562/) (2021)
- [Domain Adaptation via Maximizing Surrogate Mutual Information](https://mlsanity.com/paper/2110.12184/) (2021)
- [Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.12139/) (2022)
- [Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks](https://mlsanity.com/paper/2310.06369/) (2023)
- [Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2202.13310/) (2022)
- [Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.02739/) (2022)
- [Geometric Moment Alignment for Domain Adaptation via Siegel Embeddings](https://mlsanity.com/paper/2510.14666/) (2025)
- [Open Set Domain Recognition via Attention-Based GCN and Semantic Matching Optimization](https://mlsanity.com/paper/2105.04967/) (2021)

## Abstract (arXiv)

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of features, there are two issues to be further explored. First, the hard-assigned pseudo labels on the target domain are risky to the intrinsic data structure. Second, the batch-wise training manner in deep learning limits the description of the global structure. In this paper, a Riemannian manifold learning framework is proposed to achieve transferability and discriminability consistently. As to the first problem, this method establishes a probabilistic discriminant criterion on the target domain via soft labels. Further, this criterion is extended to a global approximation scheme for the second issue; such approximation is also memory-saving. The manifold metric alignment is exploited to be compatible with the embedding space. A theoretical error bound is derived to facilitate the alignment. Extensive experiments have been conducted to investigate the proposal and results of the comparison study manifest the superiority of consistent manifold learning framework.