# Domain Adaptation without Source Data

arXiv: https://arxiv.org/abs/2007.01524 · HTML: https://mlsanity.com/paper/2007.01524/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2020.

## Built on by (most cited first, 30 of 88)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Source-Free Domain Adaptation via Distribution Estimation](https://mlsanity.com/paper/2204.11257/) (2022)
- [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)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation](https://mlsanity.com/paper/2303.17132/) (2023)
- [If your data distribution shifts, use self-learning](https://mlsanity.com/paper/2104.12928/) (2021)
- [Towards Online Domain Adaptive Object Detection](https://mlsanity.com/paper/2204.05289/) (2022)
- [Unsupervised Domain Adaptation of Black-Box Source Models](https://mlsanity.com/paper/2101.02839/) (2021)
- [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)
- [Domain Adaptive Semantic Segmentation without Source Data](https://mlsanity.com/paper/2110.06484/) (2021)
- [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)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation](https://mlsanity.com/paper/2111.12221/) (2021)
- [Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation](https://mlsanity.com/paper/2207.13247/) (2022)
- [Unsupervised Robust Domain Adaptation without Source Data](https://mlsanity.com/paper/2103.14577/) (2021)
- [Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.12585/) (2021)
- [On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2202.00796/) (2022)
- [Few-Shot Adaptation of Pre-Trained Networks for Domain Shift](https://mlsanity.com/paper/2205.15234/) (2022)
- [The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation](https://mlsanity.com/paper/2308.09139/) (2023)
- [Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training](https://mlsanity.com/paper/2405.02954/) (2024)
- [Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.14888/) (2022)
- [Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.13986/) (2022)
- [Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.07585/) (2022)
- [In Search for a Generalizable Method for Source Free Domain Adaptation](https://mlsanity.com/paper/2302.06658/) (2023)

## Abstract (arXiv)

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real-world and possibly causes data-privacy issues, especially when the label of the source domain can be a sensitive attribute as an identifier. To avoid accessing source data that may contain sensitive information, we introduce Source data-Free Domain Adaptation (SFDA). Our key idea is to leverage a pre-trained model from the source domain and progressively update the target model in a self-learning manner. We observe that target samples with lower self-entropy measured by the pre-trained source model are more likely to be classified correctly. From this, we select the reliable samples with the self-entropy criterion and define these as class prototypes. We then assign pseudo labels for every target sample based on the similarity score with class prototypes. Furthermore, to reduce the uncertainty from the pseudo labeling process, we propose set-to-set distance-based filtering which does not require any tunable hyperparameters. Finally, we train the target model with the filtered pseudo labels with regularization from the pre-trained source model. Surprisingly, without direct usage of labeled source samples, our PrDA outperforms conventional domain adaptation methods on benchmark datasets. Our code is publicly available at https://github.com/youngryan1993/SFDA-SourceFreeDA