In this paper, we propose a new approach called Deep LogCORAL for
unsupervised visual domain adaptation. Our work builds on the recently proposed
Deep CORAL method, which proposed to train a convolutional neural network and
simultaneously minimize the Euclidean distance of convariance matrices between
the source and target domains. We propose to use the Riemannian distance,
approximated by Log-Euclidean distance, to replace the naive Euclidean distance
in Deep CORAL. We also consider first-order information, and minimize the
distance of mean vectors between two domains. We build an end-to-end model, in
which we minimize both the classification loss, and the domain difference based
on the first and second order information between two domains. Our experiments
on the benchmark Office dataset demonstrate the improvements of our newly
proposed Deep LogCORAL approach over the Deep CORAL method, as well as further
improvement when optimizing both orders of information.

本文提出了一种新的方法 ——Deep LogCORAL，用于无监督的视觉域自适应。我们使用 Riemannian 距离（由 Log-Euclidean 距离逼近）替换 Deep CORAL 中的欧几里得距离，并考虑第一和第二阶段信息。在基准 Office 数据集上的实验结果表明，相比于 Deep CORAL 方法，我们新提出的 Deep LogCORAL 方法具有更好的性能，而在优化两种信息的情况下表现得更佳。