Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from a slightly similar distribution. We propose metric-based adversarial discriminative domain adaptation (M-ADDA) which performs two main steps. First, it uses a metric learning approach to train the source model on the source dataset by optimizing the triplet loss function. This results in clusters where embeddings of the same label are close to each other and those with different labels are far from one another. Next, it uses the adversarial approach (as that used in ADDA \cite{2017arXiv170205464T}) to make the extracted features from the source and target datasets indistinguishable. Simultaneously, we optimize a novel loss function that encourages the target dataset's embeddings to form clusters. While ADDA and M-ADDA use similar architectures, we show that M-ADDA performs significantly better on the digits adaptation datasets of MNIST and USPS. This suggests that using metric-learning for domain adaptation can lead to large improvements in classification accuracy for the domain adaptation task. The code is available at \url{https://github.com/IssamLaradji/M-ADDA}.

我们提出了一种度量学习方法和对抗学习相结合的方法（M-ADDA）用于无监督领域自适应，M-ADDA在提取源和目标数据集的特征时使用了类似ADDA的结构，同时优化了一种鼓励目标数据嵌入形成聚类的新损失函数，其中表明在 MNIST 和 USPS 的数字自适应数据集上 M-ADDA 表现显著优于 ADDA，这表明使用度量学习的领域自适应可以大幅提高领域自适应任务的分类准确性。

M-ADDA：深度度量学习的无监督领域自适应