# Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation

arXiv: https://arxiv.org/abs/2106.15326 · HTML: https://mlsanity.com/paper/2106.15326/

## Key facts

- Cited by 111 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 18 Jun 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [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)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [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)
- [Dual Mixup Regularized Learning for Adversarial Domain Adaptation](https://mlsanity.com/paper/2007.03141/) (2020)
- [Generative Low-bitwidth Data Free Quantization](https://mlsanity.com/paper/2003.03603/) (2020)
- [Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis](https://mlsanity.com/paper/2007.07222/) (2020)

## Built on by (most cited first, 30 of 111)

- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [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)
- [Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition](https://mlsanity.com/paper/2107.09249/) (2021)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [Expanding Small-Scale Datasets with Guided Imagination](https://mlsanity.com/paper/2211.13976/) (2022)
- [Balancing Discriminability and Transferability for Source-Free Domain Adaptation](https://mlsanity.com/paper/2206.08009/) (2022)
- [Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning](https://mlsanity.com/paper/2211.06612/) (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)
- [Reducing the Vision and Language Bias for Temporal Sentence Grounding](https://mlsanity.com/paper/2207.13457/) (2022)
- [Disentangling Writer and Character Styles for Handwriting Generation](https://mlsanity.com/paper/2303.14736/) (2023)
- [ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation](https://mlsanity.com/paper/2205.14566/) (2022)
- [On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion](https://mlsanity.com/paper/2308.09942/) (2023)
- [Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.10856/) (2022)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation](https://mlsanity.com/paper/2312.03502/) (2023)
- [Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization](https://mlsanity.com/paper/2312.10165/) (2023)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition](https://mlsanity.com/paper/2203.04559/) (2022)
- [TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation](https://mlsanity.com/paper/2303.09870/) (2023)
- [CoNMix for Source-free Single and Multi-target Domain Adaptation](https://mlsanity.com/paper/2211.03876/) (2022)
- [Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation](https://mlsanity.com/paper/2303.00914/) (2023)
- [Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation](https://mlsanity.com/paper/2207.13247/) (2022)
- [FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation](https://mlsanity.com/paper/2304.13672/) (2023)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training](https://mlsanity.com/paper/2303.10856/) (2023)

## Abstract (arXiv)

We study a practical domain adaptation task, called source-free unsupervised domain adaptation (UDA) problem, in which we cannot access source domain data due to data privacy issues but only a pre-trained source model and unlabeled target data are available. This task, however, is very difficult due to one key challenge: the lack of source data and target domain labels makes model adaptation very challenging. To address this, we propose to mine the hidden knowledge in the source model and exploit it to generate source avatar prototypes (i.e., representative features for each source class) as well as target pseudo labels for domain alignment. To this end, we propose a Contrastive Prototype Generation and Adaptation (CPGA) method. Specifically, CPGA consists of two stages: (1) prototype generation: by exploring the classification boundary information of the source model, we train a prototype generator to generate avatar prototypes via contrastive learning. (2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes. Extensive experiments on three UDA benchmark datasets demonstrate the effectiveness and superiority of the proposed method.