提出可区分领域特征的适配器，提升无标注目标检测泛化能力
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
- 设计领域无关与领域特定双适配器，分离通用与领域特异性知识
- 在多个数据集上实现更优检测性能，显著提升跨域适应能力
- 适合研究领域自适应目标检测的学者和工业界部署开发者
领域自适应目标检测（DAOD）旨在将标注源域上训练的检测器泛化到未标注的目标域。由于视觉语言模型（VLMs）能提供对未见图像的通用知识，冻结视觉编码器并插入领域无关适配器可学习领域不变知识。然而，这种适配器不可避免地偏向源域，丢弃了对未标注目标域有用的判别性知识，即领域特定知识。为解决此问题，我们提出一种专为DAOD任务设计的新颖领域感知适配器（DA-Ada）。其核心思想是利用通用知识与领域不变知识之间的领域特定知识。DA-Ada由学习领域不变知识的领域不变适配器（DIA）和注入视觉编码器丢弃信息中的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能高效推断出领域感知的视觉编码器，从而提升领域自适应目标检测性能。代码已开源：https://github.com/Therock90421/DA-Ada。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。