Rethinking Maximum Mean Discrepancy for Visual Domain Adaptation

Wang, Wei; Li, Haojie; Ding, Zhengming; Nie, Feiping; Chen, Junyang; Dong, Xiao; Wang, Zhihui

doi:10.1109/tnnls.2021.3093468

Cited by 54 publications

(12 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adopt maximum mean discrepancy (MMD) to measure the data distribution differences between the source and target domains before and after domain adaptation. As a popular metric, the maximum mean discrepancy (MMD) has been widely used in domain adaptation research ( Kumagai and Iwata, 2019 ; Long et al, 2013 ; 2014 ; Pan et al, 2010 ; Wang et al, 2021 ; Yan et al, 2017 ), defined as follows:

where

denotes the Reproducing Kernel Hilbert Space endowed with a kernel function k , and

. If the MMD distance of source and target domains gets lower after adaptation, it indicates the data distribution difference becomes smaller.…”

Section: Empirical Evaluation Of Feature-level Data Adaptation Algori...mentioning

confidence: 99%

DomainATM: Domain adaptation toolbox for medical data analysis

Guan

Liu

2023

NeuroImage

View full text Add to dashboard Cite

where

denotes the Reproducing Kernel Hilbert Space endowed with a kernel function k , and

. If the MMD distance of source and target domains gets lower after adaptation, it indicates the data distribution difference becomes smaller.…”

Section: Empirical Evaluation Of Feature-level Data Adaptation Algori...mentioning

confidence: 99%

DomainATM: Domain adaptation toolbox for medical data analysis

Guan

Liu

2023

NeuroImage

View full text Add to dashboard Cite

“…The instance-based adaptation methods seek a strategy which selects "good" samples in the source domain to participate in model training and suppresses "bad" samples to prevent negative transfer. Kernel mean matching (KMM) [23] minimizes the maximum mean difference [24] and weighs the source data and target data in the reproducing kernel Hilbert space (RKHS), which can correct the inconsistent distribution between domains. As a classic instance-based adaptation method, transfer adaptive boosting (TrAdaBoost) [25] extends the AdaBoost algorithm to weigh source-labeled samples and target-labeled samples to match the distributions between domains.…”

Section: Domain Adaptation (Da)mentioning

confidence: 99%

Domain Adaptation Based on Semi-Supervised Cross-Domain Mean Discriminative Analysis and Kernel Transfer Extreme Learning Machine

2023

Sensors

View full text Add to dashboard Cite

Good data feature representation and high precision classifiers are the key steps for pattern recognition. However, when the data distributions between testing samples and training samples do not match, the traditional feature extraction methods and classification models usually degrade. In this paper, we propose a domain adaptation approach to handle this problem. In our method, we first introduce cross-domain mean approximation (CDMA) into semi-supervised discriminative analysis (SDA) and design semi-supervised cross-domain mean discriminative analysis (SCDMDA) to extract shared features across domains. Secondly, a kernel extreme learning machine (KELM) is applied as a subsequent classifier for the classification task. Moreover, we design a cross-domain mean constraint term on the source domain into KELM and construct a kernel transfer extreme learning machine (KTELM) to further promote knowledge transfer. Finally, the experimental results from four real-world cross-domain visual datasets prove that the proposed method is more competitive than many other state-of-the-art methods.

show abstract

“…Their objective is to enhance the generalization of a model trained on a training set (source domain) to a test set (target domain), where these two domains exhibit some degree of relevance but follow different distributions (Zhang, 2019;Jiang et al, 2022b). Recently, domain adaptation techniques have found extensive applications in computer vision tasks such as image classification (Liu et al, 2021a;Wang et al, 2022;2023b), semantic segmentation (Cheng et al, 2021;Wang et al, 2023c), and object detection (Chen et al, 2018;Saito et al, 2019;Zhu et al, 2019;Jiang et al, 2022a), delivering outstanding performance.…”

Section: Introductionmentioning

confidence: 99%

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

Luo

Wang

et al. 2023

AAAI

View full text Add to dashboard Cite

Arbitrary neural style transfer has been a popular research topic due to its rich application scenarios. Effective disentanglement of content and style is the critical factor for synthesizing an image with arbitrary style. The existing methods focus on disentangling feature representations of content and style in the spatial domain where the content and style components are innately entangled and difficult to be disentangled clearly. Therefore, these methods always suffer from low-quality results because of the sub-optimal disentanglement. To address such a challenge, this paper proposes the frequency mixer (FreMixer) module that disentangles and re-entangles the frequency spectrum of content and style components in the frequency domain. Since content and style components have different frequency-domain characteristics (frequency bands and frequency patterns), the FreMixer could well disentangle these two components. Based on the FreMixer module, we design a novel Frequency Domain Disentanglement (FDD) framework for arbitrary neural style transfer. Qualitative and quantitative experiments verify that the proposed method can render better stylized results compared to the state-of-the-art methods.

show abstract

Rethinking Maximum Mean Discrepancy for Visual Domain Adaptation

Cited by 54 publications

References 39 publications

DomainATM: Domain adaptation toolbox for medical data analysis

DomainATM: Domain adaptation toolbox for medical data analysis

Domain Adaptation Based on Semi-Supervised Cross-Domain Mean Discriminative Analysis and Kernel Transfer Extreme Learning Machine

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

Contact Info

Product

Resources

About