Locality Fisher discriminant analysis for conditional domain adaption

Zandifar, Mozhdeh; Tahmoresnezhad, Jafar

doi:10.1007/s42044-020-00062-2

Cited by 2 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compensate for this shortcoming, we can benefit from other available and relevant labeled samples. In this case, the distribution divergence between the training and test data may reduce the efficiency of the trained model on test data [1]. For an instance, suppose that for training an adaptive model to detect the pedestrians in night-time images, the day-time labeled images are employed where they are available with different distributions [2].…”

Section: Introductionmentioning

confidence: 99%

Domain Adaptation via Bregman divergence minimization

2021

Self Cite

View full text Add to dashboard Cite

In recent years, the Fisher linear discriminant analysis (FLDA) based classification models are among the most successful approaches and have shown effective performance in different classification tasks. However, when the learning data (source domain) have a different distribution compared with the testing data (target domain), the FLDA-based models may not work well, and the performance degrades, dramatically. To face this issue, we offer an optimal domain adaptation via Bregman divergence minimization (DAB) approach, in which the discriminative features of source and target domains are simultaneously learned via domain invariant representation. DAB is designed based on the constraints of FLDA, with the aim of the coupled marginal and conditional distribution shifts adaptation through Bregman divergence minimization. Thus, the resulting representation can show well functionality like FLDA and simultaneously discriminate across various classes, as well. Moreover, our proposed approach can be easily kernelized to deal with nonlinear tasks. Different experiments on various benchmark datasets demonstrate that our DAB can constructively face with the cross domain divergence and outperforms other novel state-of-the-art domain adaptation approaches in crossdistribution domains.

show abstract

Section: Introductionmentioning

confidence: 99%