Domain adaptive object detection (DAOD) aims to adapt the detector from a labelled source domain to an unlabelled target domain. In recent years, DAOD has attracted massive attention since it can alleviate performance degradation due to the large shift of data distributions in the wild. To align distributions between domains, adversarial learning is widely used in existing DAOD methods. However, the decision boundary for the adversarial domain discriminator may be inaccurate, causing the model biased towards the source domain. To alleviate this bias, we propose a novel Frequency-based Image Translation (FIT) framework for DAOD. First, by keeping domain-invariant frequency components and swapping domain-specific ones, we conduct image translation to reduce domain shift at the input level. Second, hierarchical adversarial feature learning is utilized to further mitigate the domain gap at the feature level. Finally, we design a joint loss to train the entire network in an end-to-end manner without extra training to obtain translated images. Extensive experiments on three challenging DAOD benchmarks demonstrate the effectiveness of our method.

翻译：域自适应目标检测（DAOD）旨在将检测器从有标注的源域适应到无标注的目标域。近年来，DAOD 受到广泛关注，因为它能够缓解因现实场景中数据分布巨大差异而导致的性能下降。为实现域间分布对齐，现有 DAOD 方法广泛采用对抗学习。然而，对抗域判别器的决策边界可能不准确，导致模型偏向源域。为缓解这一偏差，我们提出了一种新颖的基于频率的图像变换（FIT）框架用于 DAOD。首先，通过保留域不变频率分量并交换域特定分量，我们在输入层面进行图像变换以减小域偏移。其次，利用分层对抗特征学习进一步在特征层面缩小域差距。最后，我们设计了一个联合损失函数，以端到端方式训练整个网络，无需额外训练即可获得变换后的图像。在三个具有挑战性的 DAOD 基准测试上的大量实验证明了我们方法的有效性。