Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization

Ge, Yubin; Li, Site; Li, Xuyang; Fan, Fangfang; Xie, Wanqing; You, Jane; Liu, Xiaofeng

doi:10.1109/icassp39728.2021.9414891

“…Kang et al [14] proposed CDD, which incorporates class labels into MMD by estimating the labels of the target domain through alternating clustering, thus achieving alignment of class-conditional distributions. Ge et al [16] used the Wasserstein distance as a measure of distribution divergence and incorporated risk-aware interclass correlations into the training framework by configuring the distance matrix of the Discrete Optimal Transport (DOT) training framework. This method can better capture the similarity between the source and target domains, but adjusting the size of the distance matrix and the network structure requires some experience and expertise, and the model performance may be limited when the dataset is small.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised domain adaptation of dynamic extension networks based on class decision boundaries

Chen,

Wang,

Zhu

et al. 2024

Multimedia Systems

0

View full text Add to dashboard Cite

In response to the problems of inaccurate feature alignment, loss of source domain information, imbalanced sample distribution, and biased class decision boundaries in traditional unsupervised domain adaptation methods, this paper proposes a class decision boundary-based dynamic expansion network unsupervised domain adaptation method called CDE-Net. Specifically, our method dynamically expands the autoencoder-based network structure, which can preserve source domain feature information while gradually adapting to the target domain data distribution and learning useful feature information from the target domain. Meanwhile, by minimizing clustering loss and conditional entropy loss, CDE-Net can explore the intrinsic structure of the data and push class decision boundaries away from dense data areas. We experimentally verify our method on three medical image datasets, chest X-rays, intracranial hemorrhage, and mammography, and achieve an average AUC improvement of 25.8% or more compared to non-transfer methods. In addition, we compare our method with previous unsupervised domain adaptation methods, and the experimental results show that our method achieves better classification accuracy and generalization performance.

show abstract

“…Kang et al [14] proposed CDD, which incorporates class labels into MMD by estimating the labels of the target domain through alternating clustering, thus achieving alignment of class-conditional distributions. Ge et al [16] used the Wasserstein distance as a measure of distribution divergence and incorporated risk-aware inter-class correlations into the training framework by configuring the distance matrix of the Discrete Optimal Transport (DOT) training framework. This method can better capture the similarity between the source and target domains, but adjusting the size of the distance matrix and the network structure requires some experience and expertise, and the model performance may be limited when the dataset is small.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised domain adaptation of dynamic extension networks based on class decision boundaries

Chen

¹

,

Wang

²

,

Zhu

³

et al. 2023

Preprint

0

View full text Add to dashboard Cite

In response to the problems of inaccurate feature alignment, loss of source domain information, imbalanced sample distribution, and biased class decision boundaries in traditional unsupervised domain adaptation methods, this paper proposes a class decision boundary-based dynamic expansion network unsupervised domain adaptation method called CDE-Net. Specifically, our method dynamically expands the autoencoder-based network structure, which can preserve source domain feature information while gradually adapting to the target domain data distribution and learning useful feature information from the target domain. Meanwhile, by minimizing clustering loss and conditional entropy loss, CDE-Net can explore the intrinsic structure of the data and push class decision boundaries away from dense data areas. We experimentally verify our method on three medical image datasets, chest X-rays, intracranial hemorrhage, and mammography, and achieve an average AUC improvement of 25.8% or more compared to non-transfer methods. In addition, we compare our method with previous unsupervised domain adaptation methods, and the experimental results show that our method achieves better classification accuracy and generalization performance.

show abstract

“…In addition, the Wasserstein distance (Liu et al, 2020d;Han et al, 2020;Liu et al, 2019c;Ge et al, 2021b;Liu et al, 2019c), a.k.a. optimal transportation distance or earth mover's distance (Liu et al, 2020b,c), could be another alternative to measure the distribution divergence.…”

Section: Statistic Divergence Alignmentmentioning

confidence: 99%

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

Liu

¹

,

Yoo

²

,

Xing

³

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

Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization

Cited by 7 publications

References 20 publications

Unsupervised domain adaptation of dynamic extension networks based on class decision boundaries

Unsupervised domain adaptation of dynamic extension networks based on class decision boundaries

Unsupervised domain adaptation of dynamic extension networks based on class decision boundaries

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

Contact Info

Product

Resources

About