# When Source-Free Domain Adaptation Meets Learning with Noisy Labels

arXiv: https://arxiv.org/abs/2301.13381 · HTML: https://mlsanity.com/paper/2301.13381/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 72 references that are in the map.
- First posted on arXiv 31 Jan 2023.

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [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)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [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)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [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)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Normalized Loss Functions for Deep Learning with Noisy Labels](https://mlsanity.com/paper/2006.13554/) (2020)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Decoupling "when to update" from "how to update"](https://mlsanity.com/paper/1706.02613/) (2017)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Learning with Instance-Dependent Label Noise: A Sample Sieve Approach](https://mlsanity.com/paper/2010.02347/) (2020)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)

## Built on by (most cited first, 30 of 47)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Any-Shift Prompting for Generalization over Distributions](https://mlsanity.com/paper/2402.10099/) (2024)
- [Proxy Denoising for Source-Free Domain Adaptation](https://mlsanity.com/paper/2406.01658/) (2024)
- [Bayesian-guided Label Mapping for Visual Reprogramming](https://mlsanity.com/paper/2410.24018/) (2024)
- [Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation](https://mlsanity.com/paper/2406.06813/) (2024)
- [Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2409.04409/) (2024)
- [De-Confusing Pseudo-Labels in Source-Free Domain Adaptation](https://mlsanity.com/paper/2401.01650/) (2024)
- [Imbalanced Medical Image Segmentation with Pixel-dependent Noisy Labels](https://mlsanity.com/paper/2501.06678/) (2025)
- [Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation](https://mlsanity.com/paper/2506.21198/) (2025)
- [Probabilistic Test-Time Generalization by Variational Neighbor-Labeling](https://mlsanity.com/paper/2307.04033/) (2023)
- [Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning](https://mlsanity.com/paper/2405.18376/) (2024)
- [Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition](https://mlsanity.com/paper/2501.15519/) (2025)
- [Full spectrum Unlearnable Examples via Spectral Equalization](https://mlsanity.com/paper/2606.26719/) (2026)
- [Curriculum Guided Domain Adaptation in the Dark](https://mlsanity.com/paper/2308.00956/) (2023)
- [Domain Adaptation for Large-Vocabulary Object Detectors](https://mlsanity.com/paper/2401.06969/) (2024)
- [Improving self-training under distribution shifts via anchored confidence with theoretical guarantees](https://mlsanity.com/paper/2411.00586/) (2024)
- [GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts](https://mlsanity.com/paper/2502.12195/) (2025)
- [ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model](https://mlsanity.com/paper/2503.23529/) (2025)
- [Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation](https://mlsanity.com/paper/2510.25279/) (2025)
- [Source-Free Domain Adaptation for SSVEP-based Brain-Computer Interfaces](https://mlsanity.com/paper/2305.17403/) (2023)
- [A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective](https://mlsanity.com/paper/2402.12627/) (2024)
- [Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2505.24567/) (2025)
- [Collaborative Learning with Multiple Foundation Models for Source-Free Domain Adaptation](https://mlsanity.com/paper/2511.19147/) (2025)
- [Source-Free Domain Adaptation for Geospatial Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2601.08375/) (2026)
- [ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptation](https://mlsanity.com/paper/2603.18764/) (2026)
- [Source-Free Domain Adaptation with Vision-Language Prior](https://mlsanity.com/paper/2604.17748/) (2026)
- [Mitigating the Bias in the Model for Continual Test-Time Adaptation](https://mlsanity.com/paper/2403.01344/) (2024)
- [High-order Neighborhoods Know More: HyperGraph Learning Meets Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2405.06916/) (2024)
- [EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principles](https://mlsanity.com/paper/2407.16189/) (2024)

## Abstract (arXiv)

Recent state-of-the-art source-free domain adaptation (SFDA) methods have focused on learning meaningful cluster structures in the feature space, which have succeeded in adapting the knowledge from source domain to unlabeled target domain without accessing the private source data. However, existing methods rely on the pseudo-labels generated by source models that can be noisy due to domain shift. In this paper, we study SFDA from the perspective of learning with label noise (LLN). Unlike the label noise in the conventional LLN scenario, we prove that the label noise in SFDA follows a different distribution assumption. We also prove that such a difference makes existing LLN methods that rely on their distribution assumptions unable to address the label noise in SFDA. Empirical evidence suggests that only marginal improvements are achieved when applying the existing LLN methods to solve the SFDA problem. On the other hand, although there exists a fundamental difference between the label noise in the two scenarios, we demonstrate theoretically that the early-time training phenomenon (ETP), which has been previously observed in conventional label noise settings, can also be observed in the SFDA problem. Extensive experiments demonstrate significant improvements to existing SFDA algorithms by leveraging ETP to address the label noise in SFDA.