Transfer metric learning for unsupervised domain adaptation

Huang, Junchu; Zhou, Zhiheng

doi:10.1049/iet-ipr.2018.5871

Cited by 14 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare DMSP against the no adaptation baseline (i.e., 1-NN) and the state-of-the-art DA methods such as feature adaptation methods (i.e., transfer component analysis (TCA) [10], GFK [30], subspace alignment (SA) [12], JDA [21], group-lasso regularized optimal transport (OT-GL) [11], joint geometrical and statistical alignment (JGSA) [35], UTML [23], structure preservation and distribution alignment (SPDA) [24]), adaptive classifier learning methods (i.e., DCA [28], ARTL [15], MDDA [29]), deep DA methods (i.e., deep adaptation networks (DAN) [36], domain-adversarial neural network (DANN) [37], joint adaptation network (JAN) [38], collaborative and adversarial network (CAN) [39], conditional domain-adversarial network (CDAN) [40], domain-adversarial residual-transfer (DART) [41], multirepresentation adaptation Network (MRAN) [42], and discriminative manifold propagation (DMP) [43]).…”

Section: Methodsmentioning

confidence: 99%

“…Based on MMD, joint distribution adaptation (JDA) [21] minimizes the class-wise distribution distance between the source and target domains to match their marginal and conditional distribution difference. Furthermore, to mine discriminative information within the two domains, domain invariant and class discriminative feature learning (DICD) [22] also minimizes the intra-class scatter and maximizes the inter-class dispersion simultaneously, while unsupervised metric transfer learning method (UMTL) [23] also maximizes the inter-class distance.…”

Section: Distribution Matchingmentioning

confidence: 99%

“…Moreover, the cross-domain discrepancy still exists in the reduced latent feature space. Our DMSP minimizes the class-wise distribution distance and maximizes the interclass distance simultaneously as in [23], but in a different way. It conducts distribution matching through a classifier learning procedure, which directly obtains an adaptive classifier for the target data.…”

Section: Distribution Matchingmentioning

confidence: 99%

“…The fourth item in formula ( 1) is the inter-domain distribution adaptation regularization, which simultaneously minimizes the class-wise distribution distance between domains and maximizes the inter-class distance in the source domain as in [23], where the class-wise distribution distance is formulated as…”

Section: Problem Formulationmentioning

confidence: 99%

See 3 more Smart Citations

Distribution matching and structure preservation for domain adaptation

Zhu

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Cross-domain classification refers to completing the corresponding classification task in a target domain which lacks label information, by exploring useful knowledge in a related source domain but with different data distribution. Domain adaptation can deal with such cross-domain classification, by reducing divergence of domains and transferring the relevant knowledge from the source to the target. To mine the discriminant information of the source domain samples and the geometric structure information of domains, and thus improve domain adaptation performance, this paper proposes a novel method involving distribution matching and structure preservation for domain adaptation (DMSP). First, it aligns the subspaces of the source domain and target domain on the Grassmann manifold; and learns the non-distorted embedded feature representations of the two domains. Second, in this embedded feature space, the empirical structure risk minimization method with distribution adaptation regularization and intra-domain graph regularization is used to learn an adaptive classifier, further adapting the source and target domains. Finally, we perform extensive experiments on widely used cross-domain classification datasets to validate the superiority of DMSP. The average classification accuracy of DMSP on these datasets is the highest compared with several state-of-the-art domain adaptation methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Distribution Matchingmentioning

confidence: 99%

Section: Distribution Matchingmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

See 2 more Smart Citations

Distribution matching and structure preservation for domain adaptation

Zhu

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…We compare the MMDA approach with some state‐of‐the‐art methods, namely, GFK [21], JDA [8], TJM [31], SCA [40], JGSA [5], DMM [32], unsupervised transfer metric learning (UTML) [60], locality preserving joint transfer (LPJT) [45], and domain invariant and class discriminative feature learning (DICD) [59]. Three deep approaches, namely, AlexNet [61], deep domain confusion (DDC) [62], and deep adaptation network (DAN) [47], are also tested for comparison.…”

Section: Experiments and Evaluationsmentioning

confidence: 99%

Multi‐metric domain adaptation for unsupervised transfer learning

Yang

et al. 2020

IET image process

View full text Add to dashboard Cite

Domain adaptation metric learning method embedded with structural information for person re‐identification in internet of autonomous unmanned vehicles

Qian

2022

Softw Pract Exp

View full text Add to dashboard Cite

Internet of autonomous unmanned vehicles (IAUV) is a global network of sensors, robots, and autonomous vehicles. Person re‐identification (Re‐ID) is an important intelligent transportation application in IAUV, which needs to be solved using artificial intelligence algorithms. In this study, a domain adaptation metric learning method embedded with structural information (called DAML‐ESI) is designed for person Re‐ID in IAUV. Due to the lack of labeling information in the target domain, DAML‐ESI realizes person Re‐ID with the help of the discriminative and structural information of pedestrian images of related domains. DAML‐ESI projects pedestrian images selected from different domains into a common metric space and establishes a discriminative metric learning model, which requires that the positive sample pair be mapped to a point, and the distance distribution of the negative sample pair be mapped to a fixed value. The projection matrix learned by DAML‐ESI is used to eliminate the distribution differences between different domains, and the distance metric is used to ensure that the learned metric learning model has strong discriminative ability in the metric space. To verify the effectiveness of DAML‐ESI, experimental comparisons are conducted on three person Re‐ID datasets, and DAML‐ESI achieves satisfactory recognition performance.

show abstract

Transfer metric learning for unsupervised domain adaptation

Cited by 14 publications

References 31 publications

Distribution matching and structure preservation for domain adaptation

Distribution matching and structure preservation for domain adaptation

Multi‐metric domain adaptation for unsupervised transfer learning

Domain adaptation metric learning method embedded with structural information for person re‐identification in internet of autonomous unmanned vehicles

Contact Info

Product

Resources

About