arXiv 2412.114432024-12-16cs.CVcs.AIcs.LG

通用域自适应目标检测通过双概率对齐

Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment

CAIR, HKISI-CAS（中国科学院香港创新研究院人工智能与机器人创新研究所）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别与智能系统研究部）；The Chinese University of Hong Kong（香港中文大学）

Yuanfan Zheng, Jinlin Wu, Wuyang Li, Zhen Chen

备注：: This work is accepted by AAAI 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出双概率对齐框架，通过高斯分布建模域概率，解决通用域自适应目标检测中的私有类别对齐和特征异质性，在多种场景下超越现有方法。

摘要：

域自适应目标检测（DAOD）在闭集假设下将知识从标记的源域转移到未标记的目标域。通用域自适应目标检测（UniDAOD）将DAOD扩展到处理开集、部分集和闭集域自适应。在本文中，我们首先揭示了两个问题：域私有类别对齐对于全局级特征至关重要，以及不同层级特征之间的域概率异质性。为了解决这些问题，我们提出了一种新颖的双概率对齐（DPA）框架，将域概率建模为高斯分布，从而实现异质性域分布采样和测量。DPA由三个定制模块组成：全局级域私有对齐（GDPA）、实例级域共享对齐（IDSA）和私有类别约束（PCC）。GDPA利用全局级采样来挖掘域私有类别样本，并通过累积分布函数计算对齐权重，以解决全局级私有类别对齐问题。IDSA利用实例级采样来挖掘域共享类别样本，并通过高斯分布计算对齐权重，以进行域共享类别域对齐，从而解决特征异质性。PCC聚合特征空间和概率空间之间的域私有类别中心，以减轻负迁移。大量实验表明，我们的DPA在各种数据集和场景（包括开集、部分集和闭集）中优于最先进的UniDAOD和DAOD方法。代码可在https://github.com/zyfone/DPA获取。

英文摘要：

Domain Adaptive Object Detection (DAOD) transfers knowledge from a labeled source domain to an unannotated target domain under closed-set assumption. Universal DAOD (UniDAOD) extends DAOD to handle open-set, partial-set, and closed-set domain adaptation. In this paper, we first unveil two issues: domain-private category alignment is crucial for global-level features, and the domain probability heterogeneity of features across different levels. To address these issues, we propose a novel Dual Probabilistic Alignment (DPA) framework to model domain probability as Gaussian distribution, enabling the heterogeneity domain distribution sampling and measurement. The DPA consists of three tailored modules: the Global-level Domain Private Alignment (GDPA), the Instance-level Domain Shared Alignment (IDSA), and the Private Class Constraint (PCC). GDPA utilizes the global-level sampling to mine domain-private category samples and calculate alignment weight through a cumulative distribution function to address the global-level private category alignment. IDSA utilizes instance-level sampling to mine domain-shared category samples and calculates alignment weight through Gaussian distribution to conduct the domain-shared category domain alignment to address the feature heterogeneity. The PCC aggregates domain-private category centroids between feature and probability spaces to mitigate negative transfer. Extensive experiments demonstrate that our DPA outperforms state-of-the-art UniDAOD and DAOD methods across various datasets and scenarios, including open, partial, and closed sets. Codes are available at \url{https://github.com/zyfone/DPA}.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。