IEEE Trans Pattern Anal Mach Intell. 2018 May;40(5):1114-1127. doi: 10.1109/TPAMI.2017.2704624. Epub 2017 May 16.
Domain adaptation between diverse source and target domains is challenging, especially in the real-world visual recognition tasks where the images and videos consist of significant variations in viewpoints, illuminations, qualities, etc. In this paper, we propose a new approach for domain generalization and domain adaptation based on exemplar SVMs. Specifically, we decompose the source domain into many subdomains, each of which contains only one positive training sample and all negative samples. Each subdomain is relatively less diverse, and is expected to have a simpler distribution. By training one exemplar SVM for each subdomain, we obtain a set of exemplar SVMs. To further exploit the inherent structure of source domain, we introduce a nuclear-norm based regularizer into the objective function in order to enforce the exemplar SVMs to produce a low-rank output on training samples. In the prediction process, the confident exemplar SVM classifiers are selected and reweigted according to the distribution mismatch between each subdomain and the test sample in the target domain. We formulate our approach based on the logistic regression and least square SVM algorithms, which are referred to as low rank exemplar SVMs (LRE-SVMs) and low rank exemplar least square SVMs (LRE-LSSVMs), respectively. A fast algorithm is also developed for accelerating the training of LRE-LSSVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation, and show that our approach can also be applied to domain adaptation with evolving target domain, where the target data distribution is gradually changing. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation with fixed and evolving target domains.
不同源域和目标域之间的域自适应是具有挑战性的，特别是在现实世界的视觉识别任务中，图像和视频在视角、光照、质量等方面存在很大的变化。在本文中，我们提出了一种基于示例支持向量机（SVM）的新的域泛化和域自适应方法。具体来说，我们将源域分解为许多子域，每个子域仅包含一个正训练样本和所有负样本。每个子域的变化相对较少，预计分布更简单。通过为每个子域训练一个示例 SVM，我们得到了一组示例 SVM。为了进一步利用源域的固有结构，我们在目标函数中引入了核范数正则化项，以强制示例 SVM 在训练样本上产生低秩输出。在预测过程中，根据每个子域和目标域测试样本之间的分布不匹配，选择和重新加权置信度示例 SVM 分类器。我们基于逻辑回归和最小二乘 SVM 算法提出了我们的方法，分别称为低秩示例 SVM（LRE-SVM）和低秩示例最小二乘 SVM（LRE-LSSVM）。还开发了一种快速算法来加速 LRE-LSSVM 的训练。我们进一步扩展域自适应机（DAM）来学习最优的目标分类器进行域自适应，并且表明我们的方法也可以应用于具有演进目标域的域自适应，其中目标数据分布在逐渐变化。对象识别和动作识别的综合实验证明了我们的方法在固定和演进目标域的域泛化和域自适应方面的有效性。
