# ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation

arXiv: https://arxiv.org/abs/2205.14566 · HTML: https://mlsanity.com/paper/2205.14566/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 93 references that are in the map.
- First posted on arXiv 29 May 2022.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)
- [Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations](https://mlsanity.com/paper/2003.12237/) (2020)

## Built on by (most cited first, 30 of 34)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation](https://mlsanity.com/paper/2312.03502/) (2023)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentation](https://mlsanity.com/paper/2403.10834/) (2024)
- [Active Test-Time Adaptation: Theoretical Analyses and An Algorithm](https://mlsanity.com/paper/2404.05094/) (2024)
- [Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification](https://mlsanity.com/paper/2307.03133/) (2023)
- [STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay](https://mlsanity.com/paper/2407.15773/) (2024)
- [Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation](https://mlsanity.com/paper/2309.15575/) (2023)
- [Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology](https://mlsanity.com/paper/2404.19113/) (2024)
- [Direct Distillation between Different Domains](https://mlsanity.com/paper/2401.06826/) (2024)
- [Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification](https://mlsanity.com/paper/2210.05438/) (2022)
- [MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection](https://mlsanity.com/paper/2302.04589/) (2023)
- [Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2409.19635/) (2024)
- [AdaptGuard: Defending Against Universal Attacks for Model Adaptation](https://mlsanity.com/paper/2303.10594/) (2023)
- [Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2410.15811/) (2024)
- [Towards Practical Emotion Recognition: An Unsupervised Source-Free Approach for EEG Domain Adaptation](https://mlsanity.com/paper/2504.03707/) (2025)
- [Temporal Restoration and Spatial Rewiring for Source-Free Multivariate Time Series Domain Adaptation](https://mlsanity.com/paper/2505.21525/) (2025)
- [Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation](https://mlsanity.com/paper/2510.25279/) (2025)
- [Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning](https://mlsanity.com/paper/2310.16062/) (2023)
- [Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis](https://mlsanity.com/paper/2402.16090/) (2024)
- [Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation](https://mlsanity.com/paper/2511.19147/) (2025)
- [SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain Adaptation](https://mlsanity.com/paper/2310.08928/) (2023)
- [CNG-SFDA:Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation](https://mlsanity.com/paper/2401.14587/) (2024)
- [Reducing Bias in Pre-trained Models by Tuning while Penalizing Change](https://mlsanity.com/paper/2404.12292/) (2024)
- [Trust And Balance: Few Trusted Samples Pseudo-Labeling and Temperature Scaled Loss for Effective Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2409.00741/) (2024)
- [Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2501.01126/) (2025)
- [ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation](https://mlsanity.com/paper/2503.23712/) (2025)
- [Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation](https://mlsanity.com/paper/2505.24216/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, source-free UDA, exploiting the pre-trained source models instead of the raw source data for target learning, has been gaining popularity in recent years. Some works attempt to recover unseen source domains with generative models, however introducing additional network parameters. Other works propose to fine-tune the source model by pseudo labels, while noisy pseudo labels may misguide the decision boundary, leading to unsatisfied results. To tackle these issues, we propose an effective method named Proxy-based Mixup training with label refinery (ProxyMix). First of all, to avoid additional parameters and explore the information in the source model, ProxyMix defines the weights of the classifier as the class prototypes and then constructs a class-balanced proxy source domain by the nearest neighbors of the prototypes to bridge the unseen source domain and the target domain. To improve the reliability of pseudo labels, we further propose the frequency-weighted aggregation strategy to generate soft pseudo labels for unlabeled target data. The proposed strategy exploits the internal structure of target features, pulls target features to their semantic neighbors, and increases the weights of low-frequency classes samples during gradient updating. With the proxy domain and the reliable pseudo labels, we employ two kinds of mixup regularization, i.e., inter- and intra-domain mixup, in our framework, to align the proxy and the target domain, enforcing the consistency of predictions, thereby further mitigating the negative impacts of noisy labels. Experiments on three 2D image and one 3D point cloud object recognition benchmarks demonstrate that ProxyMix yields state-of-the-art performance for source-free UDA tasks.