In scene understanding for autonomous vehicles (AVs), models trained on the available datasets fail to generalize well to the complex, real-world scenarios with higher dynamics. In this work, we attempt to handle the distribution mismatch by employing the generative adversarial network (GAN) and weather modeling to strengthen the intra-domain data. We also alleviate the fragility of our trained models against natural distortions with state-of-the-art augmentation approaches. Finally, we assess our method for cross-domain object detection through CARLA simulation. Our experiments demonstrate that: (1) Augmenting training class with even limited intra-domain data captured from the adverse weather conditions boosts the generalization of the two kinds of object detectors; (2) Exploiting GANs and weather modeling to elaborately simulate the adverse, intra-domain weather conditions manages to surmount the adverse data scarcity issue for intra-domain object detection; (3) A combination of Augmix and style augmentations not only can promote the robustness of our trained models against different natural distortions but also can boost their performance in the cross-domain object detection; (4) Training GANs for unsupervised image-to-image translation by means of the existing, large-scale datasets outside of our training domain is found beneficial to alleviate image-based and instance-based domain shifts.

在自动驾驶汽车 (AV) 的场景理解中，在可用数据集上训练的模型无法很好地泛化到具有更高动态的复杂的现实世界场景。在这项工作中，我们尝试通过使用生成对抗网络 (GAN) 和天气建模来加强域内数据来处理分布不匹配。我们还通过最先进的增强方法减轻了我们训练模型对自然扭曲的脆弱性。最后，我们通过 CARLA 模拟评估我们的跨域对象检测方法。我们的实验表明：（1）使用从恶劣天气条件中捕获的有限域内数据来增强训练类，可以提高两种目标检测器的泛化能力；(2) 利用 GAN 和天气模型精心模拟不利情况，域内天气条件设法克服域内对象检测的不利数据稀缺问题；(3) Augmix 和风格增强的结合不仅可以提高我们训练模型对不同自然失真的鲁棒性，而且可以提高它们在跨域对象检测中的性能；(4) 通过我们训练域之外的现有大规模数据集训练 GAN 进行无监督的图像到图像转换被发现有利于缓解基于图像和基于实例的域转移。(3) Augmix 和风格增强的结合不仅可以提高我们训练模型对不同自然失真的鲁棒性，而且可以提高它们在跨域对象检测中的性能；(4) 通过我们训练域之外的现有大规模数据集训练 GAN 进行无监督的图像到图像转换被发现有利于缓解基于图像和基于实例的域转移。(3) Augmix 和风格增强的结合不仅可以提高我们训练模型对不同自然失真的鲁棒性，而且可以提高它们在跨域对象检测中的性能；(4) 通过我们训练域之外的现有大规模数据集训练 GAN 进行无监督的图像到图像转换被发现有利于缓解基于图像和基于实例的域转移。