# Visual Domain Adaptation with Manifold Embedded Distribution Alignment

arXiv: https://arxiv.org/abs/1807.07258 · HTML: https://mlsanity.com/paper/1807.07258/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 30 of 91)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Deep Subdomain Adaptation Network for Image Classification](https://mlsanity.com/paper/2106.09388/) (2021)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [Vector-Decomposed Disentanglement for Domain-Invariant Object Detection](https://mlsanity.com/paper/2108.06685/) (2021)
- [Style Normalization and Restitution for Domain Generalization and Adaptation](https://mlsanity.com/paper/2101.00588/) (2021)
- [Your Classifier can Secretly Suffice Multi-Source Domain Adaptation](https://mlsanity.com/paper/2103.11169/) (2021)
- [Personalized Transfer of User Preferences for Cross-domain Recommendation](https://mlsanity.com/paper/2110.11154/) (2021)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [Domain Generalization using Pretrained Models without Fine-tuning](https://mlsanity.com/paper/2203.04600/) (2022)
- [Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain](https://mlsanity.com/paper/2202.10725/) (2022)
- [Cross-domain Activity Recognition via Substructural Optimal Transport](https://mlsanity.com/paper/2102.03353/) (2021)
- [Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction](https://mlsanity.com/paper/2201.08029/) (2022)
- [Generalizable Sleep Staging via Multi-Level Domain Alignment](https://mlsanity.com/paper/2401.05363/) (2023)
- [Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.12585/) (2021)
- [Information-theoretic regularization for Multi-source Domain Adaptation](https://mlsanity.com/paper/2104.01568/) (2021)
- [Domain Generalisation via Risk Distribution Matching](https://mlsanity.com/paper/2310.18598/) (2023)
- [Secure Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2106.12124/) (2021)
- [FedCiR: Client-Invariant Representation Learning for Federated Non-IID Features](https://mlsanity.com/paper/2308.15786/) (2023)
- [Partial Domain Adaptation without Domain Alignment](https://mlsanity.com/paper/2108.12867/) (2021)
- [Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment](https://mlsanity.com/paper/2110.06448/) (2021)
- [Semi-supervised Domain Adaptive Structure Learning](https://mlsanity.com/paper/2112.06161/) (2021)
- [Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error](https://mlsanity.com/paper/2308.03003/) (2023)
- [Robust Domain Misinformation Detection via Multi-modal Feature Alignment](https://mlsanity.com/paper/2311.14315/) (2023)
- [Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.02089/) (2021)
- [Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks](https://mlsanity.com/paper/2202.10808/) (2022)
- [InfoOT: Information Maximizing Optimal Transport](https://mlsanity.com/paper/2210.03164/) (2022)
- [Cross Contrasting Feature Perturbation for Domain Generalization](https://mlsanity.com/paper/2307.12502/) (2023)
- [From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios](https://mlsanity.com/paper/2403.07403/) (2024)

## Abstract (arXiv)

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning. However, there are two significant challenges: (1) degenerated feature transformation, which means that distribution alignment is often performed in the original feature space, where feature distortions are hard to overcome. On the other hand, subspace learning is not sufficient to reduce the distribution divergence. (2) unevaluated distribution alignment, which means that existing distribution alignment methods only align the marginal and conditional distributions with equal importance, while they fail to evaluate the different importance of these two distributions in real applications. In this paper, we propose a Manifold Embedded Distribution Alignment (MEDA) approach to address these challenges. MEDA learns a domain-invariant classifier in Grassmann manifold with structural risk minimization, while performing dynamic distribution alignment to quantitatively account for the relative importance of marginal and conditional distributions. To the best of our knowledge, MEDA is the first attempt to perform dynamic distribution alignment for manifold domain adaptation. Extensive experiments demonstrate that MEDA shows significant improvements in classification accuracy compared to state-of-the-art traditional and deep methods.