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:域适应性对象探测(DAOD)旨在将探测器从标签源域变为无标签目标域。近年来,DAOD吸引了大量关注,因为野生数据分布的大规模转移使得它能够减缓性能退化。为了对域间分布进行统一,在现有的DAOD方法中广泛使用对抗性学习。但是,对抗性域区分器的决定界限可能不准确,导致模型偏向源域。为了减轻这种偏向,我们提议为DAOD建立一个新的基于频率的图像翻译框架。首先,通过保留域-异频元元和交换特定域域的图像转换,我们进行图像转换,以减少输入层的域转移。第二,利用等级对抗性特征学习来进一步缩小功能一级的域间差距。最后,我们设计了一个联合损失,在没有额外培训以获得翻译图像的情况下,对整个网络进行端对端培训。关于三个挑战性DOD基准的广泛实验显示了我们的方法的有效性。</s>