Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlabelled domain, i.e., domain-specific knowledge of the target domain. To solve the issue, we propose a novel Domain-Aware Adapter (DA-Ada) tailored for the DAOD task. The key point is exploiting domain-specific knowledge between the essential general knowledge and domain-invariant knowledge. DA-Ada consists of the Domain-Invariant Adapter (DIA) for learning domain-invariant knowledge and the Domain-Specific Adapter (DSA) for injecting the domain-specific knowledge from the information discarded by the visual encoder. Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection. Our code is available at https://github.com/Therock90421/DA-Ada.

翻译：领域自适应目标检测（DAOD）旨在将经过标注源域训练的检测器泛化至未标注的目标域。由于视觉-语言模型（VLMs）能够为未见图像提供必要的通用知识，冻结视觉编码器并插入一个领域无关的适配器可以学习用于DAOD的领域不变知识。然而，领域无关的适配器不可避免地偏向源域，它丢弃了未标注域上一些具有判别性的有益知识，即目标域的领域特定知识。为解决此问题，我们提出了一种专为DAOD任务设计的新型领域感知适配器（DA-Ada）。其核心在于利用介于必要通用知识与领域不变知识之间的领域特定知识。DA-Ada由用于学习领域不变知识的领域不变适配器（DIA）和用于从视觉编码器所丢弃信息中注入领域特定知识的领域特定适配器（DSA）组成。在多个DAOD任务上的综合实验表明，DA-Ada能够高效推断出一个领域感知的视觉编码器，从而提升领域自适应目标检测的性能。我们的代码发布于 https://github.com/Therock90421/DA-Ada。