# One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labeling

arXiv: https://arxiv.org/abs/2503.10020 · HTML: https://mlsanity.com/paper/2503.10020/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 30 of 31)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [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)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Bayesian Nonparametric Federated Learning of Neural Networks](https://mlsanity.com/paper/1905.12022/) (2019)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [Multiplicative Normalizing Flows for Variational Bayesian Neural Networks](https://mlsanity.com/paper/1703.01961/) (2017)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Federated Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.02054/) (2019)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023)
- [Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling](https://mlsanity.com/paper/1911.07982/) (2019)
- [KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation](https://mlsanity.com/paper/2011.09757/) (2020)
- [Your Classifier can Secretly Suffice Multi-Source Domain Adaptation](https://mlsanity.com/paper/2103.11169/) (2021)
- [Federated Learning for Computer Vision](https://mlsanity.com/paper/2308.13558/) (2023)
- [One-shot Federated Learning without Server-side Training](https://mlsanity.com/paper/2204.12493/) (2022)
- [Parametric Feature Transfer: One-shot Federated Learning with Foundation Models](https://mlsanity.com/paper/2402.01862/) (2024)
- [Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization](https://mlsanity.com/paper/2401.10272/) (2024)
- [Agile Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.05062/) (2024)
- [Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients](https://mlsanity.com/paper/2405.16304/) (2024)
- [UFDA: Universal Federated Domain Adaptation with Practical Assumptions](https://mlsanity.com/paper/2311.15570/) (2023)
- [Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignment](https://mlsanity.com/paper/2407.21311/) (2024)
- [Multi-Source Soft Pseudo-Label Learning with Domain Similarity-based Weighting for Semantic Segmentation](https://mlsanity.com/paper/2303.00979/) (2023)

## Abstract (arXiv)

Federated Learning (FL) is a promising approach for privacy-preserving collaborative learning. However, it faces significant challenges when dealing with domain shifts, especially when each client has access only to its source data and cannot share it during target domain adaptation. Moreover, FL methods often require high communication overhead due to multiple rounds of model updates between clients and the server. We propose a one-shot Federated Unsupervised Domain Adaptation (FUDA) method to address these limitations. Specifically, we introduce Scaled Entropy Attention (SEA) for model aggregation and Multi-Source Pseudo Labeling (MSPL) for target domain adaptation. SEA uses scaled prediction entropy on target domain to assign higher attention to reliable models. This improves the global model quality and ensures balanced weighting of contributions. MSPL distills knowledge from multiple source models to generate pseudo labels and manage noisy labels using smoothed soft-label cross-entropy (SSCE). Our approach outperforms state-of-the-art methods across four standard benchmarks while reducing communication and computation costs, making it highly suitable for real-world applications. The implementation code will be made publicly available upon publication.