Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain adaptation. Recently, Continuous Domain Adaptation (CDA) has emerged as an effective technique, closing this gap by utilizing a series of intermediate domains. This paper contributes a novel CDA method, W-MPOT, which rigorously addresses the domain ordering and error accumulation problems overlooked by previous studies. Specifically, we construct a transfer curriculum over the source and intermediate domains based on Wasserstein distance, motivated by theoretical analysis of CDA. Then we transfer the source model to the target domain through multiple valid paths in the curriculum using a modified version of continuous optimal transport. A bidirectional path consistency constraint is introduced to mitigate the impact of accumulated mapping errors during continuous transfer. We extensively evaluate W-MPOT on multiple datasets, achieving up to 54.1\% accuracy improvement on multi-session Alzheimer MR image classification and 94.7\% MSE reduction on battery capacity estimation.

翻译：解决训练数据与测试数据之间存在的巨大分布差异一直是机器学习领域的挑战，由此催生了迁移学习和域自适应等研究方向。近年来，连续域自适应（CDA）通过利用一系列中间域来缩小这一差距，成为一种有效技术。本文提出了一种新的CDA方法——W-MPOT，该方法严格解决了先前研究忽视的域排序和误差累积问题。具体而言，我们基于Wasserstein距离构建源域与中间域的迁移课程，这一设计受CDA理论分析的启发。随后，采用改进的连续最优传输方法，通过课程中的多条有效路径将源模型迁移至目标域。为减轻连续迁移过程中映射误差累积的影响，引入双向路径一致性约束。我们在多个数据集上对W-MPOT进行了全面评估，在多次阿尔茨海默MR图像分类任务中实现了最高54.1%的准确率提升，在电池容量估计任务中实现了94.7%的均方误差降低。