论文标题
使用最佳传输的打开设置域的适应
Open Set Domain Adaptation using Optimal Transport
论文作者
论文摘要
我们提出了一种2步最佳传输方法，该方法可以执行从源分布到目标分布的映射。在这里，目标的特殊性是介绍源域中不存在的新类。该方法的第一步旨在使用最佳运输计划拒绝这些新班级发出的样本。第二步解决了目标（级别比率）移动仍然是最佳运输问题。我们开发了一种双重方法来解决每个步骤中涉及的优化问题，我们证明我们的结果表现优于最新的最新性能。我们进一步将方法应用于源和目标分布既呈现标签变速箱又增加协变量（功能）转移以显示其稳健性的设置。
We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution. Here, the target has the particularity to present new classes not present in the source domain. The first step of the approach aims at rejecting the samples issued from these new classes using an optimal transport plan. The second step solves the target (class ratio) shift still as an optimal transport problem. We develop a dual approach to solve the optimization problem involved at each step and we prove that our results outperform recent state-of-the-art performances. We further apply the approach to the setting where the source and target distributions present both a label-shift and an increasing covariate (features) shift to show its robustness.
