Make source-free transfer great: Dynamic uncertainty-driven confident fusion for multi-source-free domain adaptation
Authors:
- Ziyun CaiZCZiyun Cai
- Jiacheng LiuJLJiacheng Liu
- Yawen HuangYHYawen Huang
- Changhui HuCHChanghui Hu
- Xian WuXWXian Wu
- Xiao-Yuan JingXJXiao-Yuan Jing
- Ling ShaoLSLing Shao
- 17 October 2025
- journal article
- Published by Elsevier in Information Fusion
- Vol. 127
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China
- Nanjing University of Posts and Telecommunications
This publication has 16 references indexed in Scilit:
- RGB-D Domain adaptive semantic segmentation with cross-modality feature recalibrationInformation Fusion, 2025
- Multi-Source Domain Adaptation by Causal-Guided Adaptive Multimodal Diffusion NetworksInternational Journal of Computer Vision, 2025
- Domain-guided conditional diffusion model for unsupervised domain adaptationNeural Networks, 2024
- Consistency-guided Multi-Source-Free Domain AdaptationEngineering Applications of Artificial Intelligence, 2024
- Unsupervised model adaptation for source-free segmentation of medical imagesMedical Image Analysis, 2024
- Generation, augmentation, and alignment: a pseudo-source domain based method for source-free domain adaptationMachine Learning, 2023
- Source-Free Unsupervised Domain Adaptation: Current research and future directionsNeurocomputing, 2023
- ProxyMix: Proxy-based Mixup training with label refinery for source-free domain adaptationNeural Networks, 2023
- Multi-source unsupervised domain adaptation for object detectionInformation Fusion, 2022
- Unsupervised Domain Adaptation in the Wild via Disentangling Representation LearningInternational Journal of Computer Vision, 2020