In the presence of large sets of labeled data, Deep Learning DL has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks. However, DL cannot always perform well when the training and testing images come from different distributions or in the presence of domain shift between training and testing images. They also suffer in the absence of labeled input data. Domain adaptation DA methods have been proposed to make up the poor performance due to domain shift. In this chapter, we present a new unsupervised deep domain adaptation method based on the alignment of second-order statistics covariances as well as maximum mean discrepancy of the source and target data with a two-stream Convolutional Neural Network CNN. We demonstrate the ability of the proposed approach to achieve state-of-the-art performance for image classification on three benchmark domain adaptation datasets: Office-31 [27], Office-Home [37] and Office-Caltech [8].
CITATION STYLE
Rahman, M. M., Fookes, C., Baktashmotlagh, M., & Sridharan, S. (2020). On Minimum Discrepancy Estimation for Deep Domain Adaptation. In Domain Adaptation for Visual Understanding (pp. 81–94). Springer International Publishing. https://doi.org/10.1007/978-3-030-30671-7_6
Mendeley helps you to discover research relevant for your work.