# BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation

arXiv: https://arxiv.org/abs/2204.02811 · HTML: https://mlsanity.com/paper/2204.02811/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 78 references that are in the map.
- First posted on arXiv 6 Apr 2022.

## Builds on (most cited first, 30 of 56)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)
- [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)
- [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)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [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)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [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)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias](https://mlsanity.com/paper/2106.03348/) (2021)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [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)

## Built on by (most cited first, 30 of 39)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception](https://mlsanity.com/paper/2303.07601/) (2023)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Bridging the Domain Gap for Multi-Agent Perception](https://mlsanity.com/paper/2210.08451/) (2022)
- [Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation](https://mlsanity.com/paper/2312.03502/) (2023)
- [Upcycling Models under Domain and Category Shift](https://mlsanity.com/paper/2303.07110/) (2023)
- [LEAD: Learning Decomposition for Source-free Universal Domain Adaptation](https://mlsanity.com/paper/2403.03421/) (2024)
- [Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training](https://mlsanity.com/paper/2405.02954/) (2024)
- [Modality-Agnostic Debiasing for Single Domain Generalization](https://mlsanity.com/paper/2303.07123/) (2023)
- [Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.07585/) (2022)
- [DEJA VU: Continual Model Generalization For Unseen Domains](https://mlsanity.com/paper/2301.10418/) (2023)
- [Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.16064/) (2024)
- [Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering](https://mlsanity.com/paper/2309.00528/) (2023)
- [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)
- [Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2311.16294/) (2023)
- [De-Confusing Pseudo-Labels in Source-Free Domain Adaptation](https://mlsanity.com/paper/2401.01650/) (2024)
- [Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation](https://mlsanity.com/paper/2310.08071/) (2023)
- [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)
- [Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data](https://mlsanity.com/paper/2412.13757/) (2024)
- [Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting](https://mlsanity.com/paper/2505.08527/) (2025)
- [Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization](https://mlsanity.com/paper/2606.21736/) (2026)
- [Generalized Unbiased Scene Graph Generation](https://mlsanity.com/paper/2308.04802/) (2023)
- [Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning](https://mlsanity.com/paper/2405.18376/) (2024)
- [Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.03795/) (2022)
- [Domain Adaptation for Large-Vocabulary Object Detectors](https://mlsanity.com/paper/2401.06969/) (2024)
- [Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2410.15811/) (2024)
- [Universal Semi-supervised Model Adaptation via Collaborative Consistency Training](https://mlsanity.com/paper/2307.03449/) (2023)
- [Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation](https://mlsanity.com/paper/2301.08413/) (2023)

## Abstract (arXiv)

Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and transmission issues. To make up for the absence of source data, most existing methods introduced feature prototype based pseudo-labeling strategies to realize self-training model adaptation. However, feature prototypes are obtained by instance-level predictions based feature clustering, which is category-biased and tends to result in noisy labels since the visual domain gaps between source and target are usually different between categories. In addition, we found that a monocentric feature prototype may be ineffective to represent each category and introduce negative transfer, especially for those hard-transfer data. To address these issues, we propose a general class-Balanced Multicentric Dynamic prototype (BMD) strategy for the SFDA task. Specifically, for each target category, we first introduce a global inter-class balanced sampling strategy to aggregate potential representative target samples. Then, we design an intra-class multicentric clustering strategy to achieve more robust and representative prototypes generation. In contrast to existing strategies that update the pseudo label at a fixed training period, we further introduce a dynamic pseudo labeling strategy to incorporate network update information during model adaptation. Extensive experiments show that the proposed model-agnostic BMD strategy significantly improves representative SFDA methods to yield new state-of-the-art results. The code is available at https://github.com/ispc-lab/BMD.