# Unsupervised Multi-source Domain Adaptation Without Access to Source Data

arXiv: https://arxiv.org/abs/2104.01845 · HTML: https://mlsanity.com/paper/2104.01845/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 5 Apr 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [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 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)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [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)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift](https://mlsanity.com/paper/1803.00830/) (2018)
- [Multi-Source Domain Adaptation with Mixture of Experts](https://mlsanity.com/paper/1809.02256/) (2018)
- [Domain Adaptive Semantic Segmentation Using Weak Labels](https://mlsanity.com/paper/2007.15176/) (2020)
- [Algorithms and Theory for Multiple-Source Adaptation](https://mlsanity.com/paper/1805.08727/) (2018)
- [Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey](https://mlsanity.com/paper/2002.12169/) (2020)
- [Nonparametric Density Estimation under Adversarial Losses](https://mlsanity.com/paper/1805.08836/) (2018)
- [Multi-source Domain Adaptation for Visual Sentiment Classification](https://mlsanity.com/paper/2001.03886/) (2020)
- [Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training](https://mlsanity.com/paper/2006.11006/) (2020)

## Built on by (most cited first, 30 of 76)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [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)
- [Balancing Discriminability and Transferability for Source-Free Domain Adaptation](https://mlsanity.com/paper/2206.08009/) (2022)
- [Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization](https://mlsanity.com/paper/2106.06916/) (2021)
- [Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts](https://mlsanity.com/paper/2210.03885/) (2022)
- [When Source-Free Domain Adaptation Meets Learning with Noisy Labels](https://mlsanity.com/paper/2301.13381/) (2023)
- [BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation](https://mlsanity.com/paper/2204.02811/) (2022)
- [INTERN: A New Learning Paradigm Towards General Vision](https://mlsanity.com/paper/2111.08687/) (2021)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2105.14138/) (2021)
- [Unsupervised Monocular Depth Estimation in Highly Complex Environments](https://mlsanity.com/paper/2107.13137/) (2021)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2209.15210/) (2022)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [CoNMix for Source-free Single and Multi-target Domain Adaptation](https://mlsanity.com/paper/2211.03876/) (2022)
- [EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition](https://mlsanity.com/paper/2403.14082/) (2024)
- [Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation](https://mlsanity.com/paper/2207.13247/) (2022)
- [Proxy Denoising for Source-Free Domain Adaptation](https://mlsanity.com/paper/2406.01658/) (2024)
- [Source-Free Domain Adaptation for Real-world Image Dehazing](https://mlsanity.com/paper/2207.06644/) (2022)
- [Cross-Modal Knowledge Transfer Without Task-Relevant Source Data](https://mlsanity.com/paper/2209.04027/) (2022)
- [On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2202.00796/) (2022)
- [Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation](https://mlsanity.com/paper/2308.14023/) (2023)
- [Effective Restoration of Source Knowledge in Continual Test Time Adaptation](https://mlsanity.com/paper/2311.04991/) (2023)
- [MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection](https://mlsanity.com/paper/2308.05988/) (2023)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.13986/) (2022)
- [Prior-guided Source-free Domain Adaptation for Human Pose Estimation](https://mlsanity.com/paper/2308.13954/) (2023)
- [LanDA: Language-Guided Multi-Source Domain Adaptation](https://mlsanity.com/paper/2401.14148/) (2024)

## Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for an unlabeled domain by transferring knowledge from a separate labeled source domain. However, most of these conventional UDA approaches make the strong assumption of having access to the source data during training, which may not be very practical due to privacy, security and storage concerns. A recent line of work addressed this problem and proposed an algorithm that transfers knowledge to the unlabeled target domain from a single source model without requiring access to the source data. However, for adaptation purposes, if there are multiple trained source models available to choose from, this method has to go through adapting each and every model individually, to check for the best source. Thus, we ask the question: can we find the optimal combination of source models, with no source data and without target labels, whose performance is no worse than the single best source? To answer this, we propose a novel and efficient algorithm which automatically combines the source models with suitable weights in such a way that it performs at least as good as the best source model. We provide intuitive theoretical insights to justify our claim. Furthermore, extensive experiments are conducted on several benchmark datasets to show the effectiveness of our algorithm, where in most cases, our method not only reaches best source accuracy but also outperforms it.