Object detection typically assumes that training and test samples are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch may lead to a significant performance drop. In this work, we present Scale-aware Domain Adaptive Faster R-CNN, a model aiming at improving the cross-domain robustness of object detection. In particular, our model improves the traditional Faster R-CNN model by tackling the domain shift on two levels: (1) the image-level shift, such as image style, illumination, etc., and (2) the instance-level shift, such as object appearance, size, etc. The two domain adaptation modules are implemented by learning domain classifiers in an adversarial training manner. Moreover, we observe that the large variance in object scales often brings a crucial challenge to cross-domain object detection. Thus, we improve our model by explicitly incorporating the object scale into adversarial training. We evaluate our proposed model on multiple cross-domain scenarios, including object detection in adverse weather, learning from synthetic data, and cross-camera adaptation, where the proposed model outperforms baselines and competing methods by a significant margin. The promising results demonstrate the effectiveness of our proposed model for cross-domain object detection. The implementation of our model is available at https://github.com/yuhuayc/sa-da-faster.

对象检测通常假设训练样本和测试样本来自相同的分布，但是实际上并不总是如此。这样的分配不匹配可能会导致性能显着下降。在这项工作中，我们提出了可感知规模的域自适应快速R-CNN，该模型旨在提高对象检测的跨域鲁棒性。特别地，我们的模型通过在两个级别上处理域偏移来改进传统的Faster R-CNN模型：（1）图像级别的偏移，例如图像样式，照明等，以及（2）实例级别的偏移（例如对象的外观，大小等）。这两个域自适应模块是通过以对抗训练的方式学习域分类器来实现的。而且，我们观察到，对象尺度的巨大差异通常会给跨域对象检测带来关键性挑战。因此，我们通过将对象比例尺明确地纳入对抗训练中来改进模型。我们在多个跨域场景中评估了我们提出的模型，包括在不利天气中进行对象检测，从合成数据中学习以及跨摄像机适应，其中提出的模型明显优于基线和竞争方法。令人鼓舞的结果证明了我们提出的模型对跨域对象检测的有效性。我们的模型的实现可在https://github.com/yuhuayc/sa-da-faster上获得。我们在多个跨域场景中评估了我们提出的模型，包括在不利天气中进行对象检测，从合成数据中学习以及跨摄像机适应，其中提出的模型明显优于基线和竞争方法。令人鼓舞的结果证明了我们提出的模型对跨域对象检测的有效性。我们的模型的实现可在https://github.com/yuhuayc/sa-da-faster上获得。我们在多个跨域场景中评估了我们提出的模型，包括在不利天气中进行对象检测，从合成数据中学习以及跨摄像机适应，其中提出的模型明显优于基线和竞争方法。令人鼓舞的结果证明了我们提出的模型对跨域对象检测的有效性。我们的模型的实现可在https://github.com/yuhuayc/sa-da-faster上获得。