1
|
Li J, Yu Z, Du Z, Zhu L, Shen HT. A Comprehensive Survey on Source-Free Domain Adaptation. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024; 46:5743-5762. [PMID: 38416606 DOI: 10.1109/tpami.2024.3370978] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/01/2024]
Abstract
Over the past decade, domain adaptation has become a widely studied branch of transfer learning which aims to improve performance on target domains by leveraging knowledge from the source domain. Conventional domain adaptation methods often assume access to both source and target domain data simultaneously, which may not be feasible in real-world scenarios due to privacy and confidentiality concerns. As a result, the research of Source-Free Domain Adaptation (SFDA) has drawn growing attention in recent years, which only utilizes the source-trained model and unlabeled target data to adapt to the target domain. Despite the rapid explosion of SFDA work, there has been no timely and comprehensive survey in the field. To fill this gap, we provide a comprehensive survey of recent advances in SFDA and organize them into a unified categorization scheme based on the framework of transfer learning. Instead of presenting each approach independently, we modularize several components of each method to more clearly illustrate their relationships and mechanisms in light of the composite properties of each method. Furthermore, we compare the results of more than 30 representative SFDA methods on three popular classification benchmarks, namely Office-31, Office-home, and VisDA, to explore the effectiveness of various technical routes and the combination effects among them. Additionally, we briefly introduce the applications of SFDA and related fields. Drawing on our analysis of the challenges confronting SFDA, we offer some insights into future research directions and potential settings.
Collapse
|
2
|
Pei J, Men A, Liu Y, Zhuang X, Chen Q. Evidential Multi-Source-Free Unsupervised Domain Adaptation. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024; 46:5288-5305. [PMID: 38315607 DOI: 10.1109/tpami.2024.3361978] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/07/2024]
Abstract
Multi-Source-Free Unsupervised Domain Adaptation (MSFUDA) requires aggregating knowledge from multiple source models and adapting it to the target domain. Two challenges remain: 1) suboptimal coarse-grained (domain-level) aggregation of multiple source models, and 2) risky semantics propagation based on local structures. In this article, we propose an evidential learning method for MSFUDA, where we formulate two uncertainties, i.e. Evidential Prediction Uncertainty (EPU) and Evidential Adjacency-Consistent Uncertainty (EAU), respectively for addressing the two challenges. The former, EPU, captures the uncertainty of a sample fitted to a source model, which can suggest the preferences of target samples for different source models. Based on this, we develop an EPU-Based Multi-Source Aggregation module to achieve fine-grained, instance-level source knowledge aggregation. The latter, EAU, provides a robust measure of consistency among adjacent samples in the target domain. Utilizing this, we develop an EAU-Guided Local Structure Mining module to ensure the trustworthy propagation of semantics. The two modules are integrated into the Evidential Aggregation and Adaptation Framework (EAAF), and we demonstrated that this framework achieves state-of-the-art performances on three MSFUDA benchmarks.
Collapse
|
3
|
Fang Y, Yap PT, Lin W, Zhu H, Liu M. Source-free unsupervised domain adaptation: A survey. Neural Netw 2024; 174:106230. [PMID: 38490115 PMCID: PMC11015964 DOI: 10.1016/j.neunet.2024.106230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 01/14/2024] [Accepted: 03/07/2024] [Indexed: 03/17/2024]
Abstract
Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in practical scenarios due to privacy protection, data storage and transmission cost, and computation burden. To tackle this issue, many source-free unsupervised domain adaptation (SFUDA) methods have been proposed recently, which perform knowledge transfer from a pre-trained source model to the unlabeled target domain with source data inaccessible. A comprehensive review of these works on SFUDA is of great significance. In this paper, we provide a timely and systematic literature review of existing SFUDA approaches from a technical perspective. Specifically, we categorize current SFUDA studies into two groups, i.e., white-box SFUDA and black-box SFUDA, and further divide them into finer subcategories based on different learning strategies they use. We also investigate the challenges of methods in each subcategory, discuss the advantages/disadvantages of white-box and black-box SFUDA methods, conclude the commonly used benchmark datasets, and summarize the popular techniques for improved generalizability of models learned without using source data. We finally discuss several promising future directions in this field.
Collapse
Affiliation(s)
- Yuqi Fang
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Pew-Thian Yap
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Weili Lin
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Hongtu Zhu
- Department of Biostatistics and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Mingxia Liu
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States.
| |
Collapse
|
4
|
Tian Q, Zhao M. Generation, division and training: A promising method for source-free unsupervised domain adaptation. Neural Netw 2024; 172:106142. [PMID: 38281364 DOI: 10.1016/j.neunet.2024.106142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2023] [Revised: 12/20/2023] [Accepted: 01/21/2024] [Indexed: 01/30/2024]
Abstract
Conventional unsupervised domain adaptation (UDA) methods often presuppose the existence of labeled source domain samples while adapting the source model to the target domain. Nevertheless, this premise is not always tenable in the context of source-free UDA (SFUDA) attributed to data privacy considerations. Some existing methods address this challenging SFUDA problem by self-supervised learning. But inaccurate pseudo-labels are always unavoidable to degrade the performance of the target model among these methods. Therefore, we propose a promising SFUDA method, namely Generation, Division and Training (GDT) which aims to promote the reliability of pseudo-labels for self-supervised learning and encourage similar features to have closer predictions than dissimilar ones by contrastive learning. Specifically in our GDT method, we first refine pseudo-labels with deep clustering for target samples and then split them into reliable samples and unreliable samples. After that, we adopt self-supervised learning and information maximization for reliable samples training. And for unreliable samples, we conduct contrastive learning via the perspective of similarity and disparity to attract similar samples and repulse dissimilar samples, which helps pull the similar features closed and push the dissimilar features away, leading to efficient feature clustering. Thorough experimentation on three benchmark datasets substantiates the excellence of our proposed approach.
Collapse
Affiliation(s)
- Qing Tian
- School of Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China; Wuxi Institute of Technology, Nanjing University of Information Science and Technology, Wuxi, 214000, China; State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China.
| | - Mengna Zhao
- School of Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China
| |
Collapse
|
5
|
Li S, Wang Z, Luo H, Ding L, Wu D. T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs. IEEE Trans Biomed Eng 2024; 71:423-432. [PMID: 37552589 DOI: 10.1109/tbme.2023.3303289] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/10/2023]
Abstract
OBJECTIVE An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-specific calibration session before each use, which is time-consuming and user-unfriendly. Transfer learning (TL) has been proposed to shorten or eliminate this calibration, but existing TL approaches mainly consider offline settings, where all unlabeled EEG trials from the new user are available. METHODS This article proposes Test-Time Information Maximization Ensemble (T-TIME) to accommodate the most challenging online TL scenario, where unlabeled EEG data from the new user arrive in a stream, and immediate classification is performed. T-TIME initializes multiple classifiers from the aligned source data. When an unlabeled test EEG trial arrives, T-TIME first predicts its labels using ensemble learning, and then updates each classifier by conditional entropy minimization and adaptive marginal distribution regularization. Our code is publicized. RESULTS Extensive experiments on three public motor imagery based BCI datasets demonstrated that T-TIME outperformed about 20 classical and state-of-the-art TL approaches. SIGNIFICANCE To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible.
Collapse
|
6
|
Sun Y, Dong W, Li X, Dong L, Shi G, Xie X. TransVQA: Transferable Vector Quantization Alignment for Unsupervised Domain Adaptation. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2024; 33:856-866. [PMID: 38231815 DOI: 10.1109/tip.2024.3352392] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/19/2024]
Abstract
Unsupervised Domain adaptation (UDA) aims to transfer knowledge from the labeled source domain to the unlabeled target domain. Most existing domain adaptation methods are based on convolutional neural networks (CNNs) to learn cross-domain invariant features. Inspired by the success of transformer architectures and their superiority to CNNs, we propose to combine the transformer with UDA to improve their generalization properties. In this paper, we present a novel model named Trans ferable V ector Q uantization A lignment for Unsupervised Domain Adaptation (TransVQA), which integrates the Transferable transformer-based feature extractor (Trans), vector quantization domain alignment (VQA), and mutual information weighted maximization confusion matrix (MIMC) of intra-class discrimination into a unified domain adaptation framework. First, TransVQA uses the transformer to extract more accurate features in different domains for classification. Second, TransVQA, based on the vector quantization alignment module, uses a two-step alignment method to align the extracted cross-domain features and solve the domain shift problem. The two-step alignment includes global alignment via vector quantization and intra-class local alignment via pseudo-labels. Third, for intra-class feature discrimination problem caused by the fuzzy alignment of different domains, we use the MIMC module to constrain the target domain output and increase the accuracy of pseudo-labels. The experiments on several datasets of domain adaptation show that TransVQA can achieve excellent performance and outperform existing state-of-the-art methods.
Collapse
|
7
|
Feng Y, Luo Y, Yang J. Cross-platform privacy-preserving CT image COVID-19 diagnosis based on source-free domain adaptation. Knowl Based Syst 2023; 264:110324. [PMID: 36713615 PMCID: PMC9869622 DOI: 10.1016/j.knosys.2023.110324] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Revised: 01/05/2023] [Accepted: 01/17/2023] [Indexed: 01/24/2023]
Abstract
In the wake of the Coronavirus disease (COVID-19) pandemic, chest computed tomography (CT) has become an invaluable component in the rapid and accurate detection of COVID-19. CT scans traditionally require manual inspections from medical professionals, which is expensive and tedious. With advancements in machine learning, deep neural networks have been applied to classify CT scans for efficient diagnosis. However, three challenges hinder this application of deep learning: (1) Domain shift across CT platforms and human subjects impedes the performance of neural networks in different hospitals. (2) Unsupervised Domain Adaptation (UDA), the traditional method to overcome domain shift, typically requires access to both source and target data. This is not realistic in COVID-19 diagnosis due to the sensitivity of medical data. The privacy of patients must be protected. (3) Data imbalance may exist between easy/hard samples and between data classes which can overwhelm the training of deep networks, causing degenerate models. To overcome these challenges, we propose a Cross-Platform Privacy-Preserving COVID-19 diagnosis network (CP 3 Net) that integrates domain adaptation, self-supervised learning, imbalanced label learning, and rotation classifier training into one synergistic framework. We also create a new CT benchmark by combining real-world datasets from multiple medical platforms to facilitate the cross-domain evaluation of our method. Through extensive experiments, we demonstrate that CP 3 Net outperforms many popular UDA methods and achieves state-of-the-art results in diagnosing COVID-19 using CT scans.
Collapse
Affiliation(s)
| | - Yuemei Luo
- School of Artificial Intelligence, Nanjing University of Information Science & Technology, China
| | - Jianfei Yang
- School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore,Corresponding author
| |
Collapse
|
8
|
Hong J, Zhang YD, Chen W. Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2022.109155] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|