# Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation

arXiv: https://arxiv.org/abs/2402.06213 · HTML: https://mlsanity.com/paper/2402.06213/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [CRIS: CLIP-Driven Referring Image Segmentation](https://mlsanity.com/paper/2111.15174/) (2021)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Soft Calibration Objectives for Neural Networks](https://mlsanity.com/paper/2108.00106/) (2021)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [Federated Semi-supervised Medical Image Classification via Inter-client Relation Matching](https://mlsanity.com/paper/2106.08600/) (2021)
- [Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting](https://mlsanity.com/paper/2005.02066/) (2020)
- [Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling](https://mlsanity.com/paper/2207.01233/) (2022)
- [Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement](https://mlsanity.com/paper/2201.01929/) (2022)
- [Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation](https://mlsanity.com/paper/2307.14709/) (2023)
- [Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation](https://mlsanity.com/paper/2401.09496/) (2024)

## Built on by (most cited first, 3 of 3)

- [LaVin-DiT: Large Vision Diffusion Transformer](https://mlsanity.com/paper/2411.11505/) (2024)
- [Source-Free Domain Adaptation with Vision-Language Prior](https://mlsanity.com/paper/2604.17748/) (2026)
- [Towards Conditional Feature Alignment for Cross-Domain Counting](https://mlsanity.com/paper/2506.17137/) (2025)

## Abstract (arXiv)

Source-free domain adaptation (SFDA) alleviates the domain discrepancy among data obtained from domains without accessing the data for the awareness of data privacy. However, existing conventional SFDA methods face inherent limitations in medical contexts, where medical data are typically collected from multiple institutions using various equipment. To address this problem, we propose a simple yet effective method, named Uncertainty-aware Adaptive Distillation (UAD) for the multi-source-free unsupervised domain adaptation (MSFDA) setting. UAD aims to perform well-calibrated knowledge distillation from (i) model level to deliver coordinated and reliable base model initialisation and (ii) instance level via model adaptation guided by high-quality pseudo-labels, thereby obtaining a high-performance target domain model. To verify its general applicability, we evaluate UAD on two image-based diagnosis benchmarks among two multi-centre datasets, where our method shows a significant performance gain compared with existing works. The code is available at https://github.com/YXSong000/UAD.