Department of Electrical Engineering, National Taipei University of Technology, Taipei 10608, Taiwan.
Sensors (Basel). 2020 Aug 5;20(16):4367. doi: 10.3390/s20164367.
In a real-world application, the images taken by different cameras with different conditions often incur illumination variation, low-resolution, different poses, blur, etc., which leads to a large distribution difference or gap between training (source) and test (target) images. This distribution gap is challenging for many primitive machine learning classification and clustering algorithms such as k-Nearest Neighbor (k-NN) and k-means. In order to minimize this distribution gap, we propose a novel Subspace based Transfer Joint Matching with Laplacian Regularization (STJML) method for visual domain adaptation by jointly matching the features and re-weighting the instances across different domains. Specifically, the proposed STJML-based method includes four key components: (1) considering subspaces of both domains; (2) instance re-weighting; (3) it simultaneously reduces the domain shift in both marginal distribution and conditional distribution between the source domain and the target domain; (4) preserving the original similarity of data points by using Laplacian regularization. Experiments on three popular real-world domain adaptation problem datasets demonstrate a significant performance improvement of our proposed method over published state-of-the-art primitive and domain adaptation methods.
在实际应用中，不同条件下的不同相机拍摄的图像往往会受到光照变化、低分辨率、不同姿势、模糊等因素的影响，这导致训练（源）和测试（目标）图像之间存在较大的分布差异或差距。对于许多原始的机器学习分类和聚类算法，如 k-最近邻（k-NN）和 k-均值，这种分布差距是一个挑战。为了最小化这种分布差距，我们提出了一种新的基于子空间的迁移联合匹配与拉普拉斯正则化（STJML）方法，用于通过联合匹配特征和对不同域中的实例进行重新加权来进行视觉域自适应。具体来说，所提出的基于 STJML 的方法包括四个关键组件：（1）考虑两个域的子空间；（2）实例重新加权；（3）同时减少源域和目标域之间边缘分布和条件分布的域偏移；（4）通过拉普拉斯正则化保持数据点的原始相似度。在三个流行的真实世界域自适应问题数据集上的实验表明，我们提出的方法在已发布的原始和域自适应方法上取得了显著的性能提升。
