Extreme Learning Machine Based on Maximum Weighted Mean Discrepancy for Unsupervised Domain Adaptation

Si, Yanna; Pu, Jiexin; Zang, Shaofei; Sun, Lei

doi:10.1109/access.2020.3047448

Cited by 10 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these approaches are developed to solve semi-supervised domain adaptation problems because they require few labeled samples from the target domains. Due to its high cost in collecting labels and labeling samples, cross-domain ELM (CDELM) [ 39 ], domain space transfer ELM (DST-ELM) [ 40 ], cross-domain extreme learning machine (CdELM) [ 41 ], and extreme learning machine based on maximum weighted mean discrepancy (ELM-MWMD) [ 42 ] are proposed respectively for unsupervised domains by minimizing the classification loss and applying the maximum mean discrepancy (MMD) strategy on the prediction results. In the above methods, the supervised ELM model usually outperforms the unsupervised ones with the help of a few labeled samples from the target domain.…”

Section: Introductionmentioning

confidence: 99%

“…In this article, inspired by pioneering works [ 38 , 42 ], we propose a novel method denoted as two-stage transfer extreme learning machine (TSTELM), in which there are two stages of domain adaptation: statistical matching and subspace alignment. At the statistical matching stage, we first learn a domain adaptation ELM classifier via utilizing the MMD to simultaneously minimize the marginal and conditional distribution between domains.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TSTELM: Two-Stage Transfer Extreme Learning Machine for Unsupervised Domain Adaptation

Zang

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

As a single-layer feedforward network (SLFN), extreme learning machine (ELM) has been successfully applied for classification and regression in machine learning due to its faster training speed and better generalization. However, it will perform poorly for domain adaptation in which the distributions between training data and testing data are inconsistent. In this article, we propose a novel ELM called two-stage transfer extreme learning machine (TSTELM) to solve this problem. At the statistical matching stage, we adopt maximum mean discrepancy (MMD) to narrow the distribution difference of the output layer between domains. In addition, at the subspace alignment stage, we align the source and target model parameters, design target cross-domain mean approximation, and add the output weight approximation to further promote the knowledge transferring across domains. Moreover, the prediction of test sample is jointly determined by the ELM parameters generated at the two stages. Finally, we investigate the proposed approach in classification task and conduct experiments on four public domain adaptation datasets. The result indicates that TSTELM could effectively enhance the knowledge transfer ability of ELM with higher accuracy than other existing transfer and non-transfer classifiers.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

TSTELM: Two-Stage Transfer Extreme Learning Machine for Unsupervised Domain Adaptation

Zang

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…In UDA [18]- [25], the source samples and unlabeled target samples are integrated for training. The knowledge from the source domain obtained by the supervision training is transferred to the target domain.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Domain Adaptation Using Explicit Class-Wise Matching for Domain-Invariant and Class-Discriminative Feature Learning

Ngo

Park

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Semi-supervised domain adaptation (SSDA) is a promising technique for various applications. It can transfer knowledge learned from a source domain having high-density labeled samples to a target domain having limited labeled samples. Several previous works have attempted to reduce the distribution discrepancy between source domain and target domain by using adversarial-based or entropybased methods. These works have improved the performance of SSDA. However, there are still lacunae in producing class-wise domain-invariant features, which impair the improvement of the classification accuracy in the target domain. We propose a novel mapping function using explicit class-wise matching that can make a better decision boundary in the embedding space for superior classification accuracy in the target domain. In general, in a target domain with low-density label samples, it is more challenging to create a well-organized distribution for the classification than in a source domain where rich label information is available. In our mapping function, a representative vector of each class in the embedding spaces of the source and target domains is derived and aligned by using class-wise matching. It is observed that the distribution in the embedding space of the source domain can be effectively reproduced in the target domain. Our method achieves outstanding accuracy of classification in the target domain compared with previous works on the Office-31, Office-Home, Visda2017 and DomainNet datasets. INDEX TERMSSemi-supervised learning, domain adaptation, classification, transfer learning, mapping function. BA HUNG NGO (Student Member, IEEE) received a B.S degree in control engineering and automation from Hanoi University of Mining and Geology, VietNam, in 2014, and an M.S degree in control engineering and automation from Hanoi University of Science and Technology, in 2016. He is currently pursuing a Ph.D. degree at Dongguk University, Rep. of Korea. His current research interests include computer vision and deep learning, especially deep transfer learning, domain adaptation, and deep learning in medical imaging. JAE HYEON PARK (S'18) received a B.S. in Electronic Engineering from Daegu University, Rep. of Korea, in 2019 and is currently pursuing an M.S. degree at Dongguk University, Rep. of Korea, Seoul. His current research interests include image analysis and enhancement, tone mapping processing, deep learning classification, panel defects evaluation. SO JEONG PARK received a B.S. in Multimedia Engineering from Dongguk University, Rep. of Korea, in 2021 and is currently pursuing an M.S. degree at Dongguk University, Rep. of Korea, Seoul. Her current research interests include semantic segmentation and domain adaptation.

show abstract

“…Therefore, we can improve the learning performance by aligning their distribution. In fact, domain adaptation [2], [3], [6], [7] can reduce the distribution divergence between source and target domains. It employs labeled source domain to boost the learning task in the target domain with few labels or even without labels.…”

Section: Introductionmentioning

confidence: 99%

“…It should be pointed out that the methods mentioned above [8], [10], [23], [24] ignore a fact that samples after projection may not be discriminative enough for the final classification. And in UDA, the labels of the target domain are not available [25].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Domain Adaptation Based on Pseudo-Label Confidence

Liu

2021

IEEE Access

View full text Add to dashboard Cite

Unsupervised domain adaptation aims to align the distributions of data in source and target domains, as well as assign the labels to data in the target domain. In this paper, we propose a new method named Unsupervised Domain Adaptation based on Pseudo-Label Confidence (UDA-PLC). Concretely, UDA-PLC first learns a new feature representation by projecting data of source and target domains into a latent subspace. In this subspace, the distribution of data in two domains are aligned and the discriminability of features in both domains is improved. Then, UDA-PLC applies structured prediction (SP) and nearest class prototype (NCP) to predicting pseudo-labels of data in the target domain, and it takes a fraction of samples with high confidence rather than all the pseudo-labeled target samples into next iterative learning. Finally, experimental results validate that the proposed method outperforms several state-of-art methods on three benchmark data sets.

show abstract

Extreme Learning Machine Based on Maximum Weighted Mean Discrepancy for Unsupervised Domain Adaptation

Cited by 10 publications

References 32 publications

TSTELM: Two-Stage Transfer Extreme Learning Machine for Unsupervised Domain Adaptation

TSTELM: Two-Stage Transfer Extreme Learning Machine for Unsupervised Domain Adaptation

Semi-Supervised Domain Adaptation Using Explicit Class-Wise Matching for Domain-Invariant and Class-Discriminative Feature Learning

Unsupervised Domain Adaptation Based on Pseudo-Label Confidence

Contact Info

Product

Resources

About