# Agile Multi-Source-Free Domain Adaptation

arXiv: https://arxiv.org/abs/2403.05062 · HTML: https://mlsanity.com/paper/2403.05062/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [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)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Safe Self-Refinement for Transformer-based Domain Adaptation](https://mlsanity.com/paper/2204.07683/) (2022)
- [Balancing Discriminability and Transferability for Source-Free Domain Adaptation](https://mlsanity.com/paper/2206.08009/) (2022)
- [Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective](https://mlsanity.com/paper/2303.13434/) (2023)
- [Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2007.08801/) (2020)
- [Zoo-Tuning: Adaptive Transfer from a Zoo of Models](https://mlsanity.com/paper/2106.15434/) (2021)
- [Dynamic Transfer for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2103.10583/) (2021)
- [On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2202.00796/) (2022)
- [AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning](https://mlsanity.com/paper/1911.09659/) (2019)

## Built on by (most cited first, 7 of 7)

- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [Understanding Knowledge Transferability for Transfer Learning: A Survey](https://mlsanity.com/paper/2507.03175/) (2025)
- [Unified modality separation: A vision-language framework for unsupervised domain adaptation](https://mlsanity.com/paper/2508.04987/) (2025)
- [Domain Generalizable Knowledge Tracing via Concept Aggregation and Relation-Based Attention](https://mlsanity.com/paper/2407.02547/) (2024)
- [One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labeling](https://mlsanity.com/paper/2503.10020/) (2025)
- [Out-of-Distribution Graph Models Merging](https://mlsanity.com/paper/2506.03674/) (2025)
- [Autonomous Source Knowledge Selection in Multi-Domain Adaptation](https://mlsanity.com/paper/2512.14710/) (2025)

## Abstract (arXiv)

Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models. This work focuses on adaptively utilizing knowledge from multiple source-pretrained models to an unlabeled target domain without accessing the source data. Despite being a practically useful setting, existing methods require extensive parameter tuning over each source model, which is computationally expensive when facing abundant source domains or larger source models. To address this challenge, we propose a novel approach which is free of the parameter tuning over source backbones. Our technical contribution lies in the Bi-level ATtention ENsemble (Bi-ATEN) module, which learns both intra-domain weights and inter-domain ensemble weights to achieve a fine balance between instance specificity and domain consistency. By slightly tuning source bottlenecks, we achieve comparable or even superior performance on a challenging benchmark DomainNet with less than 3% trained parameters and 8 times of throughput compared with SOTA method. Furthermore, with minor modifications, the proposed module can be easily equipped to existing methods and gain more than 4% performance boost. Code is available at https://github.com/TL-UESTC/Bi-ATEN.