On Minimum Discrepancy Estimation for Deep Domain Adaptation
This addresses the issue of poor performance in deep learning when training and testing data come from different distributions, which is a common problem in computer vision applications.
The paper tackles the problem of domain shift in deep learning by proposing an unsupervised domain adaptation method that aligns second-order statistics and maximum mean discrepancy between source and target data using a two-stream CNN. The method achieves state-of-the-art performance on three benchmark datasets: Office-31, Office-Home, and Office-Caltech.
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 paper, 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].