Source-Free Multidomain Adaptation With Fuzzy Rule-Based Deep Neural Networks
- Publisher:
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Publication Type:
- Journal Article
- Citation:
- IEEE Transactions on Fuzzy Systems, 2023, 31, (12), pp. 4180-4194
- Issue Date:
- 2023-12-01
Embargoed
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Source-Free Multi-Domain Adaptation with Fuzzy Rule-based Deep Neural Networks.pdf | Accepted version | 5.07 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is currently unavailable due to the publisher's embargo.
Unsupervised domain adaptation deals with a task from an unlabeled target domain by leveraging the knowledge gained from labeled source domain(s). The fuzzy system is adopted in domain adaptation to better tackle the uncertainty caused by information scarcity in the transfer. Most existing fuzzy and nonfuzzy domain adaptation methods depend on data-level distribution matching to eliminate the domain shift. However, data sharing can trigger privacy concerns. This situation results in the unavailability of source data, wherein most domain adaptation methods cannot be applied. Source-free domain adaptation is then proposed to handle this problem. But the existing source-free domain adaptation methods rarely deal with any soft information component due to data imprecision. Besides, fewer methods handle multiple source domains that provide richer transfer information. Thus, in this article, we propose source-free multidomain adaptation with fuzzy rule-based deep neural networks, which takes advantage of a fuzzy system to handle data uncertainty in domain adaptation without source data. To learn source private models with high generality, which is important to collect low-noise pseudotarget labels, auxiliary tasks are designed by jointly training source models from multiple domains, which share source parameters and fuzzy rules while protecting source data. To transfer fuzzy rules and fit source private parameters to the target domain, self-supervised learning and anchor-based alignment are built to force target data into source feature spaces. Experiments on real-world datasets under both homogeneous and heterogeneous label space scenarios are carried out to validate the proposed method. The results indicate the superiority of the proposed fuzzy rule-based source-free multidomain adaptation method.
Please use this identifier to cite or link to this item: