面向特征生成的无监督域适应算法

针对无标签高维图像分类问题，常用的深度网络在无标签的情况下难以产生好的分类结果。为此，提出一种面向特征生成的无监督域适应模型(Feature-GAN)，它以一种无监督的方式在特征层面学习从一个域到另一个域转换，将源域图像特征映射为目标域图像特征并保持标签信息，生成的带标签特征可用于目标域特征的分类训练。该模型在复杂图像域适应上避免了图像本身的生成过程，而专注于特征生成，易训练且稳定性高。实验表明，该方法可以广泛应用于复杂图像分类的场景，相比于传统基于样本生成的无监督域适应算法，该算法在精确度、收敛速度以及稳定性上均有提高。

Unsupervised Feature-Level Domain Adaptation with Generative Adversarial Networks

For the classification problem of unlabeled high-dimensional images, the commonly used deep neutral networks have difficulty in producing good classification results in the unlabeled datasets. This paper proposes an unsupervised feature-level domain adaptation with generative adversarial networks (Feature-GAN), which learns the feature level transformation from one domain to another in unsupervised manner. It maps the source domain image features to the target domain image features and keeps the label information, and these generated labeled features can be used to train a classifier adapted to the target domain features. This model avoids the generation process of the image itself in the complex image domain adaptation problem and focuses on feature generation. The model is easy to train and has high stability. Experiments show that the proposed method can be widely applied to complex image classification scenarios, and it outperforms traditional sample generation-based unsupervised domain adaptation algorithms in terms of accuracy, convergence speed, and stability.