Changes in environmental conditions, geographical variability and different sensor properties typically make it almost impossible to employ previously trained classifiers for new data without a significant drop in classification accuracy. Domain adaptation (DA) techniques been proven useful to alleviate that problem. In particular, appearance adaptation techniques may be used to adapt images from a specific dataset in such a way that the generated images have a style that is similar to the images from another dataset. Such techniques are, however, prone to creating artifacts that hinder proper classification of the adapted images. In this work we propose an unsupervised DA approach for change detection tasks, which is based on a particular appearance adaptation method: the Cycle-Consistent Generative Adversarial Network (CycleGAN). Specifically, we extend that method by introducing additional constraints in the training phase of the model components, which make it preserve the semantic structure and class transitions in the adapted images. We evaluate the proposed approach on a deforestation detection application, considering different sites in the Amazon rain-forest and in the Brazilian Cerrado (savanna) using Landsat-8 images. In the experiments, each site corresponds to a domain, and the accuracy of a classifier trained with images and references from one (source) domain is measured in the classification of another (target) domain. The results show that the proposed approach is successful in producing artifact-free adapted images, which can be satisfactory classified by the pre-trained source classifiers. On average, the accuracies achieved in the classification of the adapted images outperformed the baselines (when no adaptation was made) by 7.1% in terms of mean average precision, and 9.1% in terms of F1-Score. To the best of our knowledge, the proposed method is the first unsupervised domain adaptation approach devised for change detection.

环境条件的变化、地理可变性和不同的传感器特性通常使得几乎不可能在不显着降低分类精度的情况下使用先前训练的分类器来处理新数据。域适应 (DA) 技术已被证明可用于缓解该问题。特别地，外观适应技术可用于以生成的图像具有与来自另一数据集的图像相似的风格的方式来适应来自特定数据集的图像。然而，这种技术容易产生阻碍对适应图像进行正确分类的伪影。在这项工作中，我们提出了一种用于变化检测任务的无监督 DA 方法，该方法基于特定的外观适应方法：循环一致生成对抗网络 (CycleGAN)。具体来说，我们通过在模型组件的训练阶段引入额外的约束来扩展该方法，这使其保留了适应图像中的语义结构和类转换。我们使用 Landsat-8 图像考虑了亚马逊雨林和巴西塞拉多（稀树草原）中的不同地点，评估了在森林砍伐检测应用程序上提出的方法。在实验中，每个站点对应一个域，用来自一个（源）域的图像和参考训练的分类器的准确性在另一个（目标）域的分类中被测量。结果表明，所提出的方法成功地产生了无伪影的自适应图像，可以通过预训练的源分类器进行令人满意的分类。一般，适应图像分类的准确率在平均平均精度方面比基线（未进行适应时）高 7.1%，在 F1-Score 方面高 9.1%。据我们所知，所提出的方法是第一个为变化检测而设计的无监督域适应方法。