Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain. To address the large domain gap issue between the source and target domains, we propose a novel regularization method for domain adaptive object detection, BlenDA, by generating the pseudo samples of the intermediate domains and their corresponding soft domain labels for adaptation training. The intermediate samples are generated by dynamically blending the source images with their corresponding translated images using an off-the-shelf pre-trained text-to-image diffusion model which takes the text label of the target domain as input and has demonstrated superior image-to-image translation quality. Based on experimental results from two adaptation benchmarks, our proposed approach can significantly enhance the performance of the state-of-the-art domain adaptive object detector, Adversarial Query Transformer (AQT). Particularly, in the Cityscapes to Foggy Cityscapes adaptation, we achieve an impressive 53.4% mAP on the Foggy Cityscapes dataset, surpassing the previous state-of-the-art by 1.5%. It is worth noting that our proposed method is also applicable to various paradigms of domain adaptive object detection. The code is available at:https://github.com/aiiu-lab/BlenDA

通过生成中间领域的伪样本及其对应的软域标签以进行自适应训练，我们提出了一种用于领域自适应目标检测的新型正则化方法 BlenDA，旨在解决源域与目标域之间存在的较大领域差异问题。根据两个适应性基准的实验结果，我们提出的方法能显著提高最先进的领域自适应目标检测器 Adversarial Query Transformer (AQT) 的性能，在 Cityscapes 至 Foggy Cityscapes 自适应中，我们在 Foggy Cityscapes 数据集上实现了53.4%的平均准确率(mAP)，超过了先前的最先进方法1.5%。值得注意的是，我们提出的方法也适用于各种领域自适应目标检测范式。

BlenDA：通过基于扩散的混合实现域自适应目标检测