# Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

arXiv: https://arxiv.org/abs/2002.08681 · HTML: https://mlsanity.com/paper/2002.08681/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 30 of 43)

- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks](https://mlsanity.com/paper/2207.05444/) (2022)
- [Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective](https://mlsanity.com/paper/2303.13434/) (2023)
- [Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models](https://mlsanity.com/paper/2403.17589/) (2024)
- [Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve](https://mlsanity.com/paper/2102.03924/) (2021)
- [Compound Domain Generalization via Meta-Knowledge Encoding](https://mlsanity.com/paper/2203.13006/) (2022)
- [Task-specific Inconsistency Alignment for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15345/) (2022)
- [Unsupervised Domain Adaptation of Black-Box Source Models](https://mlsanity.com/paper/2101.02839/) (2021)
- [Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation](https://mlsanity.com/paper/2312.03502/) (2023)
- [Self-Adversarial Disentangling for Specific Domain Adaptation](https://mlsanity.com/paper/2108.03553/) (2021)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Conditional Bures Metric for Domain Adaptation](https://mlsanity.com/paper/2108.00302/) (2021)
- [LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models](https://mlsanity.com/paper/2407.08966/) (2024)
- [Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data](https://mlsanity.com/paper/2412.06284/) (2024)
- [AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models](https://mlsanity.com/paper/2410.20149/) (2024)
- [Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners](https://mlsanity.com/paper/2106.00417/) (2021)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment](https://mlsanity.com/paper/2110.06448/) (2021)
- [Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2211.06841/) (2022)
- [Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting](https://mlsanity.com/paper/2302.04832/) (2023)
- [On Universal Black-Box Domain Adaptation](https://mlsanity.com/paper/2104.04665/) (2021)
- [Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization](https://mlsanity.com/paper/2108.08995/) (2021)
- [Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization](https://mlsanity.com/paper/2302.05110/) (2023)
- [Concept-Based Unsupervised Domain Adaptation](https://mlsanity.com/paper/2505.05195/) (2025)
- [Deep Domain Generalization with Feature-norm Network](https://mlsanity.com/paper/2104.13581/) (2021)
- [Domain Gap Estimation for Source Free Unsupervised Domain Adaptation with Many Classifiers](https://mlsanity.com/paper/2207.05785/) (2022)
- [Maximizing Conditional Independence for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2203.03212/) (2022)

## Abstract (arXiv)

In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring Disagreement (MCSD) divergence is presented by aggregating the absolute margin violations in multi-class classification, and this proposed MCSD is able to fully characterize the relations between any pair of multi-class scoring hypotheses. By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains. Consequently, an algorithmic framework of Multi-class Domain-adversarial learning Networks (McDalNets) is developed, and its different instantiations via surrogate learning objectives either coincide with or resemble a few recently popular methods, thus (partially) underscoring their practical effectiveness. Based on our identical theory for multi-class UDA, we also introduce a new algorithm of Domain-Symmetric Networks (SymmNets), which is featured by a novel adversarial strategy of domain confusion and discrimination. SymmNets affords simple extensions that work equally well under the problem settings of either closed set, partial, or open set UDA. We conduct careful empirical studies to compare different algorithms of McDalNets and our newly introduced SymmNets. Experiments verify our theoretical analysis and show the efficacy of our proposed SymmNets. In addition, we have made our implementation code publicly available.