Unsupervised domain adaptation for segmentation with black-box source model

Liu, Xiaofeng; Yoo, Chaehwa; Xing, Fangxu; Kuo, C.-C. Jay; Fakhri, Georges El; Kang, Je-Won; Woo, Jonghye

doi:10.1117/12.2607895

Cited by 11 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, recently, Yin et al (2020a) propose a deep inversion technique to demonstrate that original training data can be recovered from knowledge used in the course of white-box domain adaptation . To address this, a recent work (Liu et al, 2022h) uses black-box UDA segmentation, for which no prior knowledge of network weights is needed for adaptation. Liu et al (2022i) further propose that a target domain network structure could be different from a trained source domain model to achieve UDA for segmentation.…”

Section: Source-free Domain Adaptationmentioning

confidence: 99%

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Liu

Yoo

Xing

et al. 2022

SIP

Self Cite

View full text Add to dashboard Cite

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success usually relies on two assumptions: (i) vast troves of labeled datasets are required for accurate model fitting, and (ii) training and testing data are independent and identically distributed. Its performance on unseen target domains, thus, is not guaranteed, especially when encountering out-of-distribution data at the adaptation stage. The performance drop on data in a target domain is a critical problem in deploying deep neural networks that are successfully trained on data in a source domain. Unsupervised domain adaptation (UDA) is proposed to counter this, by leveraging both labeled source domain data and unlabeled target domain data to carry out various tasks in the target domain. UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc. In this review, as a rapidly evolving topic, we provide a systematic comparison of its methods and applications. In addition, the connection of UDA with its closely related tasks, e.g., domain generalization and out-of-distribution detection, has also been discussed. Furthermore, deficiencies in current methods and possible promising directions are highlighted.

show abstract

Section: Source-free Domain Adaptationmentioning

confidence: 99%

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Liu

Yoo

Xing

et al. 2022

SIP

Self Cite

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, this is the first attempt at achieving UDA for deep segmentation networks using black-box domain adaptation. Our prior work showed an initial network design and concept (Liu et al, 2022 ). Building upon that work, the present study describes refined network architectures and provides extensive validations on a few different datasets and network backbones.…”

Section: Introductionmentioning

confidence: 99%

“…However, that work cannot be directly applied to the segmentation task to perform pixel-wise classification. Additionally, a few attempts have been made to carry out black-box domain adaptation (Liu et al, 2022 ), although they could be used in more challenging yet realistic clinical scenarios.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Black-Box Model Domain Adaptation for Brain Tumor Segmentation

et al. 2022

Self Cite

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) is an emerging technique that enables the transfer of domain knowledge learned from a labeled source domain to unlabeled target domains, providing a way of coping with the difficulty of labeling in new domains. The majority of prior work has relied on both source and target domain data for adaptation. However, because of privacy concerns about potential leaks in sensitive information contained in patient data, it is often challenging to share the data and labels in the source domain and trained model parameters in cross-center collaborations. To address this issue, we propose a practical framework for UDA with a black-box segmentation model trained in the source domain only, without relying on source data or a white-box source model in which the network parameters are accessible. In particular, we propose a knowledge distillation scheme to gradually learn target-specific representations. Additionally, we regularize the confidence of the labels in the target domain via unsupervised entropy minimization, leading to performance gain over UDA without entropy minimization. We extensively validated our framework on a few datasets and deep learning backbones, demonstrating the potential for our framework to be applied in challenging yet realistic clinical settings.

show abstract

“…Building upon SFDA, one novel setting, Black-Box Domain Adaptation (BBDA) [15], has been considered as a more challenging task, where only the application programming interface (API) of the pre-trained model, including its predictions and features, are provided. Prior BBDA methods [15,16] The objectives of employing transfer learning techniques for medical image segmentation in this thesis can be summarized as follows:…”

Section: 22 Residual Block Bymentioning

confidence: 99%

“…Their experiments on different classification tasks on BBDA setting achieved state-of-the-art performance. In the field of biomedical engineering, Liu et al [16] trained the student network using knowledge distillation loss and entropy minimization loss, which demonstrated effectiveness in various medical segmentation tasks.…”

Section: Self-supervised Knowledge Distillationmentioning

confidence: 99%

Domain adaptation in biomedical engineering: unsupervised, source-free, and black box approaches

Yuan

View full text Add to dashboard Cite

The remarkable advancements in deep learning methodologies over recent years can be attributed to the availability of large, high-quality labeled datasets, intricate network structures, and the swift progression of hardware technologies. However, in the biomedical engineering, the scarcity of data often poses a significant challenge in training a well-generalized model. This thesis delves into the potential of transfer learning methods as a viable solution to this data scarcity issue. The research provides a comprehensive exploration of Transfer Learning (TL), Unsupervised Domain Adaptation (UDA), Source-Free Domain Adaptation (SFDA), and Black-Box Domain Adaptation (BBDA) within the realm of biomedical engineering. It tackles the issue of data dependency in deep learning, with a particular emphasis on the application of TL in fine-tuning neural networks for specialized tasks. The study further investigates UDA techniques, specifically in the context of cross-dataset EEG classification tasks, and proposes entropy minimization-based methodologies to alleviate domain shifts. The thesis also scrutinizes SFDA in the context of medical imaging segmentation and abnormal ECG classification, introducing three innovative methodologies to overcome inherent challenges. Expanding on SFDA, the thesis evaluates the efficiency and accuracy of BBDA in real-time applications for cross-subject EEG driver drowsiness detection. This research contributes novel insights into handling data dependency, domain shifts, and privacy concerns in biomedical engineering, advocating for a nuanced approach where the scope of achievements is judiciously balanced against the challenges posed by scarce data.

show abstract

Unsupervised domain adaptation for segmentation with black-box source model

Cited by 11 publications

References 25 publications

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Unsupervised Black-Box Model Domain Adaptation for Brain Tumor Segmentation

Domain adaptation in biomedical engineering: unsupervised, source-free, and black box approaches

Contact Info

Product

Resources

About