# LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

arXiv: https://arxiv.org/abs/2403.03421 · HTML: https://mlsanity.com/paper/2403.03421/

## Key facts

- Cited by 25 papers in the map (data through 7 Oct 2026).
- Builds on 48 of its 69 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [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)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [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)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Efficient Domain Generalization via Common-Specific Low-Rank Decomposition](https://mlsanity.com/paper/2003.12815/) (2020)
- [Learning to Balance Specificity and Invariance for In and Out of Domain Generalization](https://mlsanity.com/paper/2008.12839/) (2020)
- [No More Discrimination: Cross City Adaptation of Road Scene Segmenters](https://mlsanity.com/paper/1704.08509/) (2017)

## Built on by (most cited first, 25 of 25)

- [GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editing](https://mlsanity.com/paper/2412.02366/) (2024)
- [Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.16064/) (2024)
- [USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation](https://mlsanity.com/paper/2602.08431/) (2026)
- [HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation](https://mlsanity.com/paper/2407.12387/) (2024)
- [Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Framework](https://mlsanity.com/paper/2411.12558/) (2024)
- [MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection](https://mlsanity.com/paper/2403.04149/) (2024)
- [GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning](https://mlsanity.com/paper/2403.14410/) (2024)
- [Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model](https://mlsanity.com/paper/2407.14208/) (2024)
- [Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation](https://mlsanity.com/paper/2506.03521/) (2025)
- [Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2507.21367/) (2025)
- [Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation](https://mlsanity.com/paper/2410.11271/) (2024)
- [Training-Free Label Space Alignment for Universal Domain Adaptation](https://mlsanity.com/paper/2509.17452/) (2025)
- [Domain-invariant Representation Learning via Segment Anything Model for Blood Cell Classification](https://mlsanity.com/paper/2408.07467/) (2024)
- [Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2504.11992/) (2025)
- [Beyond Retraining: Training-Free Unknown Class Filtering for Source-Free Open Set Domain Adaptation of Vision-Language Models](https://mlsanity.com/paper/2504.14224/) (2025)
- [From Entanglement to Alignment: Representation Space Decomposition for Unsupervised Time Series Domain Adaptation](https://mlsanity.com/paper/2507.20968/) (2025)
- [Frustratingly Easy Feature Reconstruction for Out-of-Distribution Detection](https://mlsanity.com/paper/2509.06988/) (2025)
- [Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2509.11264/) (2025)
- [Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation](https://mlsanity.com/paper/2510.00478/) (2025)
- [Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation](https://mlsanity.com/paper/2511.18711/) (2025)
- [Autonomous Source Knowledge Selection in Multi-Domain Adaptation](https://mlsanity.com/paper/2512.14710/) (2025)
- [Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation](https://mlsanity.com/paper/2606.00808/) (2026)
- [LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2607.17653/) (2026)
- [Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation](https://mlsanity.com/paper/2608.19890/) (2026)
- [A Comprehensive Benchmark of Source-Free Universal Domain Adaptation on Time Series Representations](https://mlsanity.com/paper/2609.39810/) (2026)

## Abstract (arXiv)

Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to source data, which tends to be more practical due to data protection policies. The main challenge lies in determining whether covariate-shifted samples belong to target-private unknown categories. Existing methods tackle this either through hand-crafted thresholding or by developing time-consuming iterative clustering strategies. In this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify target-private data. Technically, LEAD initially leverages the orthogonal decomposition analysis for feature decomposition. Then, LEAD builds instance-level decision boundaries to adaptively identify target-private data. Extensive experiments across various UniDA scenarios have demonstrated the effectiveness and superiority of LEAD. Notably, in the OPDA scenario on VisDA dataset, LEAD outperforms GLC by 3.5% overall H-score and reduces 75% time to derive pseudo-labeling decision boundaries. Besides, LEAD is also appealing in that it is complementary to most existing methods. The code is available at https://github.com/ispc-lab/LEAD.