A Multistage Framework With Mean Subspace Computation and Recursive Feedback for Online Unsupervised Domain Adaptation
A Multistage Framework With Mean Subspace Computation and Recursive Feedback for Online Unsupervised Domain Adaptation
复制标题
DOI：
10.1109/tip.2022.3186537
复制
发表时间：
2022-06
影响因子：
10.6
通讯作者：
Ji-Sun Moon;Debasmit Das;C. S. George Lee
中科院分区：
文献类型：
--
作者：
Ji-Sun Moon;Debasmit Das;C. S. George Lee
针对在线无监督领域自适应(OUDA)问题，提出了一种新的多阶段框架来解决目标数据无标记、批量在线的情况。对于Ouda问题，传统的基于流形的方法大多侧重于将每个到达的目标数据转换到源域，而没有充分考虑到达的目标数据之间的时间相关性和累积统计量。为了将数据从源域和目标域投影到一个公共子空间，并实时处理投影的数据，我们提出了一种新的方法，称为均值-子空间增量计算(ICMS)技术，该方法计算Grassmann流形上均值-目标子空间的近似值，并被证明是接近Karcher均值的。此外，在递归反馈阶段，从平均值-目标子空间计算的变换矩阵被应用于下一个目标数据，使目标数据更接近源域。变换矩阵的计算和下一个目标子空间的预测通过考虑Grassmann流形上目标子空间流之间的累积时间相关性来利用递归反馈阶段的性能。通过预先训练好的源分类器对变换后的目标数据的标签进行预测，然后用变换后的数据和预测的标签来更新分类器。在六个数据集上进行了广泛的实验，深入研究了我们提出的框架中每个阶段的影响和贡献，以及它在分类精度和计算速度方面的性能。此外，在传统的基于流形的学习模型和基于神经网络的学习模型上的实验证明了该框架对各种类型的学习模型的适用性。
In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem and propose a novel multi-stage framework to solve real-world situations when the target data are unlabeled and arriving online sequentially in batches. Most of the traditional manifold-based methods on the OUDA problem focus on transforming each arriving target data to the source domain without sufficiently considering the temporal coherency and accumulative statistics among the arriving target data. In order to project the data from the source and the target domains to a common subspace and manipulate the projected data in real-time, our proposed framework institutes a novel method, called an Incremental Computation of Mean-Subspace (ICMS) technique, which computes an approximation of mean-target subspace on a Grassmann manifold and is proven to be a close approximate to the Karcher mean. Furthermore, the transformation matrix computed from the mean-target subspace is applied to the next target data in the recursive-feedback stage, aligning the target data closer to the source domain. The computation of transformation matrix and the prediction of next-target subspace leverage the performance of the recursive-feedback stage by considering the cumulative temporal dependency among the flow of the target subspace on the Grassmann manifold. The labels of the transformed target data are predicted by the pre-trained source classifier, then the classifier is updated by the transformed data and predicted labels. Extensive experiments on six datasets were conducted to investigate in depth the effect and contribution of each stage in our proposed framework and its performance over previous approaches in terms of classification accuracy and computational speed. In addition, the experiments on traditional manifold-based learning models and neural-network-based learning models demonstrated the applicability of our proposed framework for various types of learning models.