# Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment

arXiv: https://arxiv.org/abs/1907.02271 · HTML: https://mlsanity.com/paper/1907.02271/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2019.

## Built on by (most cited first, 12 of 12)

- [Unsupervised Model Adaptation for Source-free Segmentation of Medical Images](https://mlsanity.com/paper/2211.00807/) (2022)
- [Secure Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2106.12124/) (2021)
- [Improved Region Proposal Network for Enhanced Few-Shot Object Detection](https://mlsanity.com/paper/2308.07535/) (2023)
- [Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Data](https://mlsanity.com/paper/2301.12361/) (2023)
- [Increasing Model Generalizability for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2209.14644/) (2022)
- [Cross-Domain Distribution Alignment for Segmentation of Private Unannotated 3D Medical Images](https://mlsanity.com/paper/2410.09210/) (2024)
- [Domain Adaptation Broad Learning System Based on Locally Linear Embedding](https://mlsanity.com/paper/2106.14367/) (2021)
- [Robust Internal Representations for Domain Generalization](https://mlsanity.com/paper/2309.15522/) (2023)
- [Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations](https://mlsanity.com/paper/2401.01035/) (2024)
- [Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2401.01042/) (2024)
- [Unsupervised Domain Adaptation Using Compact Internal Representations](https://mlsanity.com/paper/2401.07207/) (2024)
- [Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud](https://mlsanity.com/paper/2410.02720/) (2024)

## Abstract (arXiv)

We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target visual domains is minimized. We use the output space of a shared cross-domain deep encoder to model the embedding space anduse the Sliced-Wasserstein Distance (SWD) to measure and minimize the distance between the embedded distributions of two source and target domains to enforce the embedding to be domain-agnostic.Additionally, we use the source domain labeled data to train a deep classifier from the embedding space to the label space to enforce the embedding space to be discriminative.As a result of this training scheme, we provide an effective solution to train the deep classification network on the source domain such that it will generalize well on the target domain, where only unlabeled training data is accessible. To mitigate the challenge of class matching, we also align corresponding classes in the embedding space by using high confidence pseudo-labels for the target domain, i.e. assigning the class for which the source classifier has a high prediction probability. We provide experimental results on UDA benchmark tasks to demonstrate that our method is effective and leads to state-of-the-art performance.