# Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1705.00609 · HTML: https://mlsanity.com/paper/1705.00609/

## Key facts

- Cited by 151 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2017.

## Built on by (most cited first, 30 of 151)

- [Deep Subdomain Adaptation Network for Image Classification](https://mlsanity.com/paper/2106.09388/) (2021)
- [Robust Mean Teacher for Continual and Gradual Test-Time Adaptation](https://mlsanity.com/paper/2211.13081/) (2022)
- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests](https://mlsanity.com/paper/2106.00545/) (2021)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13575/) (2021)
- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering](https://mlsanity.com/paper/2206.02721/) (2022)
- [Cross-category Video Highlight Detection via Set-based Learning](https://mlsanity.com/paper/2108.11770/) (2021)
- [SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks](https://mlsanity.com/paper/2207.07888/) (2022)
- [LLMs are Good Action Recognizers](https://mlsanity.com/paper/2404.00532/) (2024)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation](https://mlsanity.com/paper/2108.07142/) (2021)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [A Comprehensive Review of Digital Twin -- Part 1: Modeling and Twinning Enabling Technologies](https://mlsanity.com/paper/2208.14197/) (2022)
- [Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification](https://mlsanity.com/paper/2101.12521/) (2021)
- [Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.01286/) (2021)
- [Action Segmentation with Mixed Temporal Domain Adaptation](https://mlsanity.com/paper/2104.07461/) (2021)
- [Towards Discriminative Representation Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2108.03439/) (2021)
- [Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2105.02001/) (2021)
- [A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning](https://mlsanity.com/paper/2204.00951/) (2022)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training](https://mlsanity.com/paper/2303.10856/) (2023)
- [Learning Domain-Aware Detection Head with Prompt Tuning](https://mlsanity.com/paper/2306.05718/) (2023)
- [Population Aware Diffusion for Time Series Generation](https://mlsanity.com/paper/2501.00910/) (2025)
- [Unsupervised Structure-Texture Separation Network for Oracle Character Recognition](https://mlsanity.com/paper/2205.06549/) (2022)
- [Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation](https://mlsanity.com/paper/2107.06154/) (2021)
- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [Unaligned Image-to-Image Translation by Learning to Reweight](https://mlsanity.com/paper/2109.11736/) (2021)

## Abstract (arXiv)

In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted as a discrepancy metric between the distributions of source and target domains. However, existing MMD-based domain adaptation methods generally ignore the changes of class prior distributions, i.e., class weight bias across domains. This remains an open problem but ubiquitous for domain adaptation, which can be caused by changes in sample selection criteria and application scenarios. We show that MMD cannot account for class weight bias and results in degraded domain adaptation performance. To address this issue, a weighted MMD model is proposed in this paper. Specifically, we introduce class-specific auxiliary weights into the original MMD for exploiting the class prior probability on source and target domains, whose challenge lies in the fact that the class label in target domain is unavailable. To account for it, our proposed weighted MMD model is defined by introducing an auxiliary weight for each class in the source domain, and a classification EM algorithm is suggested by alternating between assigning the pseudo-labels, estimating auxiliary weights and updating model parameters. Extensive experiments demonstrate the superiority of our weighted MMD over conventional MMD for domain adaptation.