School of Multidisciplinary Sciences, The Graduate University for Advanced Studies (SOKENDAI), Shonan Village, Hayama, Kanagawa 240-0193, Japan; KONICA MINOLTA, INC., 2970 Ishikawa-machi, Hachioji, Tokyo 192-8505, Japan.
Department of Statistical Modeling, The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa, Tokyo 190-8562, Japan; Center for Advanced Intelligence Project (AIP), RIKEN, 1-4-4 Nihonbashi, Chuo-ku, Tokyo 103-0027, Japan.
Neural Netw. 2023 Jul;164:731-741. doi: 10.1016/j.neunet.2023.03.035. Epub 2023 Mar 27.
In domain adaptation, when there is a large distance between the source and target domains, the prediction performance will degrade. Gradual domain adaptation is one of the solutions to such an issue, assuming that we have access to intermediate domains, which shift gradually from the source to the target domain. In previous works, it was assumed that the number of samples in the intermediate domains was sufficiently large; hence, self-training was possible without the need for labeled data. If the number of accessible intermediate domains is restricted, the distances between domains become large, and self-training will fail. Practically, the cost of samples in intermediate domains will vary, and it is natural to consider that the closer an intermediate domain is to the target domain, the higher the cost of obtaining samples from the intermediate domain is. To solve the trade-off between cost and accuracy, we propose a framework that combines multifidelity and active domain adaptation. The effectiveness of the proposed method is evaluated by experiments with real-world datasets.
在域自适应中，当源域和目标域之间存在较大距离时，预测性能将会下降。渐进式域自适应是解决此类问题的方法之一，假设我们可以访问从源域逐渐过渡到目标域的中间域。在以前的工作中，假设中间域中的样本数量足够大；因此，可以在不需要标记数据的情况下进行自训练。如果可访问的中间域数量受到限制，则域之间的距离会变大，自训练将失败。实际上，中间域中的样本成本会有所不同，并且考虑到与目标域越接近的中间域，从中获取样本的成本就越高，这是很自然的。为了解决成本和准确性之间的权衡问题，我们提出了一种结合多保真度和主动域自适应的框架。通过使用真实数据集的实验评估了所提出方法的有效性。
